Lara 3 became generally available, while Lara Think added more control over reasoning and support for visual context. SOC 2 Type II is another headline for organizations evaluating Lara Translate for business use.

The integrations announced last month also moved forward: Lara Translate is now publicly available for Slack and published in the Make Marketplace. Audio Translation arrived on iOS and Android, and TBX glossary import and export reached the web app.

Here are the Lara Translate October 2026 updates: what shipped, and why it matters.

Lara 3 is now generally available

When you translate professionally, a fluent sentence is only the starting point. The terminology, meaning, and tone also need to survive the move into another language.

Lara 3, the third generation of Translated’s translation-specialized AI model, became generally available in October through Lara Translate, the Lara API, and TranslationOS.

In Translated’s blind evaluation of 16,800 translations from English into 21 enterprise languages, professional translators judged around 82% of Lara 3 translations accurate without edits. Lara 3 ranked first in 20 of the 21 language pairs tested.

For translators and localization teams, the practical question is how much work remains after the first translation. These results provide a useful starting point for testing Lara 3 against your own content and review standards.

Read the Lara 3 announcement and evaluation results.

Lara Think: more control over reasoning, with visual context

Some translation decisions need a closer look. An expression may carry a cultural meaning, or a short product label may be impossible to interpret without seeing what it describes.

Lara Think analyzes the source before producing and revising a translation. October adds selectable reasoning effort levels, allowing developers to balance deeper analysis with processing time.

Lara Think text translation also accepts an accompanying image or image URL through the API and supported SDKs. A screenshot, packaging image, or product photograph can provide context that the words alone leave out. Image context is currently exclusive to Lara Think.

There is benchmark news, too. As of October 20, 2026, Lara 3 Think ranked first on the Last Translation Benchmark’s Blind leaderboard, with a 56.09% pass rate on its 911-item evaluation set. The test focuses on difficult examples that leading translation systems had failed, including slang, idioms, and cultural references.

Read more about Lara Think and the benchmark.

SOC 2 Type II: supporting enterprise security reviews

Translation quality is one part of choosing a service for business use. Security teams also need evidence about how the provider manages and protects the information entrusted to it.

SOC 2 Type II is another major milestone this month. For organizations evaluating Lara Translate, it supports the due diligence process that accompanies the adoption of a new translation service.

The Translated Trust Center is the starting point for reviewing published security information and requesting access to supporting documentation. Procurement, IT, and security teams can use it to assess the relevant evidence and clarify how it applies to their intended use of Lara Translate.

Explore the Translated Trust Center.

Lara Translate reaches Slack and Make

September’s article introduced Slack and Make as integrations going through review. October brings both into users’ workflows.

Translate within Slack conversations

Lara Translate for Slack is now publicly available. Multilingual teams can access Lara within Slack, reducing the need to move content between a workplace conversation and a separate translation tool.

This is particularly useful when translation is part of an ongoing exchange: understanding a colleague’s message, preparing a reply, or sharing information across teams working in different languages.

The app is available for public distribution. A Slack Marketplace listing is still pending, so public availability and Marketplace listing remain separate milestones.

Add translation to Make automations

Lara for Make is approved and published in the Make Marketplace. You can now incorporate Lara translation capabilities into automation scenarios connecting your applications and business processes.

For teams with repeatable translation tasks, this provides a way to make translation one step in a broader workflow, without building a custom integration from scratch.

Explore Lara Translate in the Make Marketplace.

Audio Translation arrives on iOS and Android

A voice message or interview recording should be as easy to translate as a paragraph of text.

Audio Translation is now available on both iOS and Android. You can record directly in Lara, choose an existing audio file, or send audio from another app through your phone’s sharing options. Once translated, the audio can be played and shared from the mobile experience.

This makes the feature useful for voice messages, interviews, and other recordings where the voice is part of the experience.

Each app also makes use of its platform’s native controls. On Android, recording supports press-and-hold capture, hands-free operation, and background recording with a persistent notification. You can pause, preview, and resume a recording.

On iOS, Live Activities and Dynamic Island let you follow recording, upload, and translation progress after leaving the app.

Get Lara Translate on your phone

Download the app and keep translation ready when you need it.

Download for Android | Download for iOS

TBX glossary import and export, now in the web app

If your team already maintains a termbase, bringing that terminology into Lara should fit the way you work.

You can now import and export glossaries in TBX format directly through the Lara Translate web app. TBX, short for TermBase eXchange, is a format used to exchange terminology databases between translation and localization tools.

September introduced TBX support through the API and SDK. October brings the same capability to people managing glossaries through the web interface.

For translators and terminology managers, this removes the need to convert a TBX termbase into CSV before importing it into Lara. You can also export Lara glossaries in TBX format for use elsewhere in your localization workflow.

For developers, existing API and SDK support continues to provide a programmatic route for exchanging terminology. Teams can work through the web app or their own integrations using the same exchange format.

Explore the Lara Translate developer documentation.

Try October’s updates with your own content

Start with a translation you know well: a product description with specific terminology, a passage with an ambiguous expression, or a voice message you need to share in another language.

Use it to assess Lara 3, explore Lara Think’s reasoning capabilities, or try the new mobile audio workflow. If translation is a recurring part of your team’s work, Slack, Make, and TBX glossary exchange give you more ways to connect Lara to that process.

Try Lara Translate.

FAQ

Are Slack and Make both available?

Yes. Lara Translate for Slack is publicly available, although its Slack Marketplace listing is still pending. Lara for Make is published in the Make Marketplace.

What changed for Lara Think in October?

Developers can choose reasoning effort levels and provide an image or image URL as context for text translation through the API and supported SDKs.

Can I translate audio on my phone?

Yes. Both the iOS and Android apps support recording or importing audio, translating it, and playing or sharing the result.

Is TBX support new this month?

TBX import and export is new in the web app. Support through the API and SDK was introduced previously.

This article is about

• Lara 3’s general availability
• Lara Think reasoning controls, image context, and benchmark results
• SOC 2 Type II and enterprise security reviews
• Lara Translate integrations for Slack and Make
• Audio Translation on iOS and Android
• TBX glossary import and export in the web app

L'articolo Lara Translate October 2026 Updates: Lara 3, Think, and more proviene da Blog | Lara Translate.

Errors like this slip through because the output looks fluent. The Last Translation Benchmark was built to collect exactly these cases. As of 20 October 2026, Lara 3 Think, the reasoning model in Lara Translate, tops its leaderboard with a 56.09% pass rate. Here’s how the benchmark works, how the scores compare, and when reasoning is worth the extra seconds.

What is the Last Translation Benchmark?

The Last Translation Benchmark (LTB) is an academic project led by Vilém Zouhar, with ETH Zurich among its core institutions. It brings together 260 contributors from 177 institutions. Its first release, LTBv1, contains 3,456 human-written, peer-reviewed examples across 109 languages, covering text, images, audio, and video.

The selection rule is strict. An example was accepted only if most leading machine translation systems got it wrong. Why so harsh? The authors argue that existing translation benchmarks are close to saturation, so a harder test was needed to separate the best systems.

The result leans heavily on informal and culture-bound language. Across the full dataset, the paper’s labels include 986 cultural artifacts and 453 slang items. The leaderboard scores models on LTBv1-eval, a 911-item, text-only subset.

How the Last Translation Benchmark is scored

Every example comes with pass/fail rules written by the contributor who submitted it. A rule might say that “Pfund” has to become 500 g, or that a proverb has to keep its figurative meaning. A translation passes only if it meets every rule.

An LLM checks each translation against those rules. The live leaderboard currently uses Gemini 3.8 Flash as the verifier, while the paper’s interactive verification used Gemini 3.1 Pro. The paper reports a Kendall τb of 90.5 (on a 0 to 100 scale) between the verifier’s system rankings and human rankings. It also recommends open-source LLMs as verifiers for the highest reproducibility.

Funding is disclosed, too. The paper thanks Cohere, Google, and OpenAI for financial support to run the platform at scale, and Charles University for server infrastructure.

The leaderboard has two modes. Every figure in this article comes from the main Blind mode, where models translate without seeing the rules or the human reference.

Last Translation Benchmark results (October 2026)

Top AI systems on LTBv1-eval, Blind mode, as of 20 October 2026. Source: LTB leaderboard.

Human translations by the benchmark contributors score 99.89%, which sets the ceiling.

Lara 3 Think leads the next system by almost 11 percentage points. That’s roughly 98 more sentences translated correctly out of 911, on a test where every item was picked because leading systems failed it. Lara 3 Think ran with the Fluid style and no adaptation at all: no context, translation memories, glossaries or custom instructions.

A quick note on names. Lara Think is the reasoning mode in Lara Translate. Lara 3 Think is its current version, built on Lara 3, and Lara 2 Think Pro belongs to the previous generation.

Why do Lara Base and Lara Think score so differently?

The same leaderboard lists an earlier standard Lara model (a November 2025 entry) at 0.66%. That figure says more about how the run went than about the quality of the translations. Our logs from those benchmark runs show a long list of technical errors, caused mainly by differences between the standard input formats Lara Translate expects and the formats used to run the benchmark. The public dataset reflects this: 200 of the 911 evaluation items have no Lara output at all, and every one of them counts as a fail.

We’re working with the benchmark team to fix the integration and run the evaluation again, so the leaderboard reflects what Lara Translate actually delivers.

What is Lara Think and how does it work?

Lara Think is the reasoning model in Lara Translate. Before it commits to a translation, it runs a multi-step linguistic analysis of the source, takes glossaries, style guides, and context into account when they’re available, and then revises its own output.

Lara 3 also introduced a training phase. The model generates alternative translations, an automatic judge scores them, and the model refines itself over millions of cycles. According to Translated, Lara Think “cuts errors nearly in half when higher quality is required.”

The trade-off is time. Lara Think can take up to 10x longer than Lara Base. For developers, a callback can return a fast preliminary translation first while the reasoned version completes.

What kinds of errors does the benchmark catch?

These items come from the LTBv1 evaluation set. Each one shows what the source means and what a frontier model produced.

Examples from LTBv1-eval with Gemini 3.1 Pro output.

None of these outputs is ungrammatical. Each one passes a quick read, and each one changes the meaning. In professional settings, that’s the most expensive kind of error: nobody flags it until a customer, a reader, or a court does.

Who is Lara Think for?

Pick Lara Think when a wrong nuance costs more than a few extra seconds:

• Marketing and brand copy, where tone and wordplay carry the message
• If you handle legal, financial or regulated content, one term can change an obligation
• Publishing and editorial work with dialogue and informal registers
• Reviews, social posts and other user-generated content full of slang
• Building a quality-critical localization pipeline? This is the model for it.

For real-time chat, very high volumes, or latency-sensitive workflows, Lara Base is the better fit. Speed matters more there than the last few hard cases.

How to try Lara Think

Developers enable Lara Think through the Lara Translate API by passing reasoning: true in the options object. The developer documentation covers SDKs, callbacks and pricing.

The bottom line

Benchmarks built from easy sentences can no longer tell strong translation systems apart. The Last Translation Benchmark can, because every item is a trap. On that test, Lara 3 Think leads by almost 11 points, and the reasoning step is the reason. Use it where a missed nuance is expensive, and keep Lara Base for speed.

FAQ

What is the Last Translation Benchmark?

The Last Translation Benchmark is an academic test of AI translation built from human-written examples that most leading machine translation systems get wrong. Its first release, LTBv1, has 3,456 examples across 109 languages, submitted by 260 contributors from 177 institutions.

Which AI translator scored highest on the Last Translation Benchmark?

Lara 3 Think, the reasoning model in Lara Translate, scored highest with a 56.09% pass rate on the 911-item LTBv1-eval set in Blind mode, as of 20 October 2026. GPT-6 Astra Pro is second at 45.33%.

How is the Last Translation Benchmark scored?

An LLM verifier checks each translation against pass/fail rules written by the contributor, and a translation passes only if it meets all of them. The live leaderboard uses Gemini 3.8 Flash as the verifier.

What is Lara Think?

Lara Think is the reasoning model in Lara Translate. It analyzes the source text in several steps before translating, which improves accuracy on ambiguous, informal and culture-bound content.

What’s the difference between Lara Think and Lara Base?

Lara Base is the default model, optimized for speed and consistency on professional content. Lara Think adds a reasoning layer for higher quality and can take up to 10x longer.

How much does Lara Think cost?

Lara Think costs €2,000 per million source characters on the Pro plan and €1,500 on the Team plan, through the Lara Translate API. It isn’t available on the Free plan.

This article is about

• Lara 3 Think ranks first on the Last Translation Benchmark with 56.09%, almost 11 points ahead of GPT-6 Astra Pro.
• How the benchmark is built: 3,456 examples that leading AI translators failed, from 260 contributors in 109 languages.
• Why an LLM verifier with contributor-written rules scores the results, and who funds the platform.
• Why reasoning, not raw translation training, decides performance on slang, idioms and cultural references.
• When to choose Lara Think over Lara Base, and what it costs through the API.

Sources

• Last Translation Benchmark: leaderboard
• Last Translation Benchmark paper (arXiv 2609.04173)
• LTBv1 dataset on Hugging Face
• Introducing Lara 3 (Translated)
• Translate Text: Lara Translate for Developers

L'articolo Last Translation Benchmark: Lara Think Ranks First proviene da Blog | Lara Translate.

Lara is the translation model behind Lara Translate, built by Translated. Its third generation, Lara 3, became generally available in October 2026, after a first release to selected partners in July. You can now use Lara 3 in Lara Translate, the Lara API, and TranslationOS. Here’s what the evaluation found, why it matters if you translate for a living or at scale, and where to try it.

How do you test a translation model fairly?

Grading your own homework is easy. It’s also not very convincing. So the evaluation put Lara 3’s output in front of professional translators, blind: they saw each translation without knowing whether it came from Lara 3, GPT-5.6 Sol, Claude Fable 5, DeepL, or Google Translate.

The test covered 16,800 translations from English into 21 enterprise languages. Part of the material came from WMT25, the 2025 edition of a standard public machine translation benchmark that spans books, news, and user conversations. The rest was proprietary enterprise content from travel, technology, and finance, which is the kind of text companies actually send out for localization.

How often did Lara 3 translations need no edits?

Translators care about one practical question: can I use this as it is? Around four in five Lara 3 translations were judged accurate, meaning they needed no edits at all. For the strongest general-purpose model in the test, the figure was roughly two in three.

Averaged across all 21 language pairs, the scores came out like this.

Average scores from blind professional evaluations of 16,800 translations, English into 21 enterprise languages. Source: Translated, October 2026.

Lara 3 ranked first in 20 of the 21 language pairs.

Where does Lara 3 make the biggest difference?

Enterprise localization is where most translation tools start to wobble. The approved term every single time, the same product name across hundreds of strings, a voice that sounds like the brand in every market: that’s a lot to hold at once. According to Translated, Lara 3’s advantage was most evident in exactly this kind of work, where terminology, context, consistency, and brand voice matter most.

This is the job Lara was built for. In Lara Translate, Lara works with your glossaries and translation memories, so the terms and phrasing your team has already approved carry over into every new translation.

What happens when you need to translate a lot, fast?

Localizing a product catalog, a help center, or a steady stream of support tickets turns speed and budget into hard limits. A model that translates well but slowly, or well but expensively, forces you to pick which content gets translated at all. Nobody likes that trade-off.

In a separate single-thread benchmark, Lara 3 delivered 23 times the throughput of Claude Fable 5. For the same budget, it translated 3.75 times as many characters. For teams working at volume, that means more content shipped per day and per euro.

How was Lara 3 trained?

Most translation models learn by imitating. They study translations people have already made and learn to do the same. The problem is that a sentence can often be translated correctly in more than one way, so a model that only copies can only be as good as the examples it learned from.

For Lara 3, Translated added one more step to the model’s training, and it works a lot like practice. Lara translates the same sentence in several different ways. A judge, built from the work of professional reviewers, scores each version and points out every mistake, down to a single word that doesn’t fit. Lara learns from the versions that scored well, corrects the mistakes, and starts again. Millions of times. You can read the full technical story in our introduction to Lara 3.

Why build a model only for translation?

Lara is built to do one thing: translate. Translated has been building language technology since 1999, and designing a model around a single purpose was a bet the company made early. The Lara 3 results show that a translation-specialized model can outperform the largest general-purpose AI models in a field where accuracy is non-negotiable.

Marco Trombetti, founder and CEO of Translated, put it this way:

Translation is a particularly unforgiving domain for AI as technical fluency alone is not enough. An ambiguous meaning, an incorrect term or a missed cultural cue can render a translation inaccurate and unusable. We’ve always believed that understanding these intricacies deeply and building a model specifically designed to grapple with them, is the only way to deliver genuinely quality translation. Lara 3’s performance is proof that our approach works. These results show what is possible when you commit to developing AI with one defining purpose. You don’t need to be the biggest player in AI to lead, you need to know exactly what problem you’re addressing and how to solve it.

Where can you use Lara 3?

If you translate on your own or as part of a team, you’ll find Lara 3 in Lara Translate, the online AI translator for text and documents in 200+ languages.

Enterprises and professional translators can also work with Lara 3 through the Lara API, which plugs the model into your own products and pipelines, and through TranslationOS, Translated’s AI service delivery platform. Building with the API? Start with the Lara Translate developer documentation.

The bottom line

Reading blind, professional translators preferred Lara 3 over the biggest general-purpose AI models and the best-known translation tools. It gets more translations right the first time, it’s faster, and it stretches the same budget further. The quickest way to judge it is to hand it something you actually need translated.

FAQ

What is Lara 3?

Lara 3 is the third generation of Lara, the translation-specialized AI model developed by Translated. It powers Lara Translate and is also available through the Lara API and TranslationOS.

When was Lara 3 released?

Lara 3 became generally available in October 2026. Translated first released it to selected partners in July 2026.

Is Lara 3 better than DeepL and Google Translate?

In blind evaluations by professional translators, yes: Lara 3 averaged 82% across 21 language pairs, against 57% for DeepL and 53% for Google Translate. It also scored ahead of GPT-5.6 Sol (69%) and Claude Fable 5 (67%), and ranked first in 20 of the 21 pairs.

How was Lara 3 evaluated?

Professional translators reviewed 16,800 translations from English into 21 enterprise languages without knowing which system produced each one. The content combined the WMT25 public benchmark (books, news, and user conversations) with proprietary enterprise material from the travel, technology, and finance sectors.

Is Lara 3 faster than general-purpose AI models?

Yes. In a single-thread benchmark, Lara 3 delivered 23 times the throughput of Claude Fable 5 and translated 3.75 times as many characters for the same budget.

How can I start using Lara 3?

Open Lara Translate, the online AI translator, to use Lara 3 for text and documents. Enterprises and professional translators can also access Lara 3 through the Lara API and TranslationOS.

This article is about

• Lara 3, Translated’s translation-specialized AI model, reaching general availability in October 2026
• A blind evaluation in which professional translators scored 16,800 translations into 21 enterprise languages
• Lara 3’s 82% average score against GPT-5.6 Sol, Claude Fable 5, DeepL, and Google Translate
• Why enterprise localization, with its terminology and brand voice demands, showed the widest gap
• Throughput and cost results against Claude Fable 5, plus the “learning by doing” training phase
• Using Lara 3 in Lara Translate, the Lara API, and TranslationOS

Sources

• Translated Announces General Availability of LARA 3, MultiLingual
• Introducing Lara 3, Translated
• Lara 3 Overview (benchmark methodology), Translated

This article was produced by the Lara Translate content team. Lara Translate is an AI translation platform built by Translated, with more than 25 years of professional translation experience. Individuals, teams, and enterprises use Lara Translate to translate text and documents with Lara 3, across 200+ languages and 70+ file formats.

L'articolo Lara 3 Is Now Available: The Translation Model Professional Translators Preferred in Blind Tests proviene da Blog | Lara Translate.

The headline is Lara Translate in ChatGPT: the plugin is now published, so you can translate without leaving the conversation. For teams, a new Group Admin role makes Lara Translate easier to run as an organization grows. My Translations reached its first production release across web, iOS, and Android. And there is more across mobile and the developer tools.

Here are the Lara Translate September 2026 updates: what shipped, and why it matters.

Lara Translate is now available in ChatGPT

A lot of drafting, research, and content work already happens inside ChatGPT. Until now, translating any of it meant leaving that flow, running the text through another tool, and bringing the result back.

The Lara Translate plugin for ChatGPT is now live. It maps Lara Translate’s existing MCP tools into the OpenAI environment, so you can use Lara Translate’s context-aware translation directly inside a ChatGPT conversation, as part of your research, writing, and content work.

You can find and install Lara Translate from the ChatGPT Plugins Directory. Once installed, you can invoke it directly in a conversation, including through an @ mention or from the + menu where available. Availability can depend on your plan and workspace settings.

This is the first of several. The Lara Translate integrations for Claude, Slack, and Make are currently going through their respective marketplace review processes.

Open Lara Translate in ChatGPT.

What’s new for teams: the Group Admin role

As a team grows, one person often ends up managing everything: who belongs where, which glossaries and translation memories each part of the business can use, and how usage breaks down by department. That becomes hard to sustain in larger, more distributed organizations.

Groups were introduced to address two recurring needs from larger customers: keeping linguistic resources separated, and reporting usage by organizational unit. With Groups, an organization can keep Translation Memories and Glossaries separated between different parts of the business, for example so a Legal team does not draw on resources meant for Marketing. Group-level usage reporting then gives clearer visibility into how Lara Translate is being consumed across teams or departments.

September adds the Group Admin role for Team accounts, including Enterprise accounts, which run on Team plans with additional needs. A Team Owner can now delegate the day-to-day management of an individual Group to a dedicated Group Admin, while keeping ownership of the overall Team account. The difference is one of scope: a Team Owner owns and controls the entire Team account, while a Group Admin manages a single Group on the Owner’s behalf. This makes Lara Translate easier to operate as responsibilities spread across a larger organization.

See how Groups and resource sharing work in Lara Translate.

My Translations, now across web and mobile

You translate a paragraph, refine it until it reads right, then move on and lose it. The next time the same text comes up, you start over.

My Translations reached its first production release, and it is available across the web app, iOS, and Android. You can save a text translation, including the source, the translated content, and any edits you made, then reopen it, edit it again, or remove it when you no longer need it. It gives you a persistent personal library of useful translation work to return to without repeating the original workflow.

On mobile, you can save directly from the Text view and open your collection from the bookmark entry point or from Account, then Resources. This first milestone focuses on the core save, browse, retrieve, edit, and delete experience across every platform.

Learn how My Translations works.

What’s new for image translation: Generative mode in the web app

When you translate an image, the new text rarely fits the old space. A short phrase runs long, a caption shifts, and the layout can end up looking patched together.

Generative Image Translation is now available directly in the Lara Translate web app. You can choose between two modes depending on the result you need. Inpainting replaces the original text while keeping most of the image unchanged. Generative mode recreates the image around the translated content, adapting typography, spacing, and layout for a more natural and visually consistent result.

This brings a capability previously available through Lara Translate’s developer ecosystem directly to web-app users, and gives you control over the trade-off between cost, visual fidelity, and how much of the original image is modified.

And it’s also available on our mobile apps!

Get Lara Translate on your phone

Save translations, use Meaning in Context, and sign in with SSO, all from your phone.

Download for Android | Download for iOS

What’s new on mobile: SSO on iOS and Meaning in Context

Two mobile updates stand out this month, one for organizations and one for anyone working with an unfamiliar text.

Single Sign-On is now on iOS. Eligible users can access Lara Translate with their organization’s company credentials. Alongside SSO, we improved sign-up and login reliability, including authentication flows that could unexpectedly end an active session.

Meaning in Context is now live on both iOS and Android. You can view the meaning of an individual word directly within the text you are translating, with the explanation generated from the surrounding context. It is most useful for ambiguous words or expressions whose meaning depends on the surrounding context, thereby extending Lara Translate toward contextual language understanding.

See how Meaning in Context works.

What’s new for developers: TBX glossaries and EPUB

Professional localization and publishing teams work with formats of their own, and moving into a new tool should not mean converting all of them first.

Glossaries now support native TBX. Lara Translate supports TBX (TermBase eXchange) for Glossary import and export through the SDK, so you can bring existing terminology databases into Lara Translate and export Lara Translate Glossaries in TBX format without first converting them to CSV. This improves interoperability with CAT tools and existing localization workflows. Support in the web app is planned for release in the next few days.

EPUB is now a supported Document Translation format. Document Translation supports EPUB files through the SDK, in addition to the Lara Translate web app. Developers can integrate EPUB translation directly into automated publishing and localization workflows without first converting files into an intermediate format, which makes EPUB a first-class format across both interactive and programmatic workflows.

Explore the Lara Translate developer documentation.

What to expect next

September’s shipped updates, the ChatGPT plugin, the Group Admin role, My Translations across web and mobile, Generative Image Translation in the web app, SSO and Meaning in Context on mobile, and TBX and EPUB support in the SDK, are built around one theme: making Lara Translate available in more places and easier to run at scale.

A few more things are already moving. The Lara Translate integrations for Claude, Slack, and Make are in marketplace review, TBX import and export is planned for the web app in the next few days, and work has started on a new Lara Translate web app design. You can follow the full changelog on the What’s New page.

FAQ

How do I use Lara Translate in ChatGPT?

Install the Lara Translate plugin from the ChatGPT Plugins Directory. Once installed, you can invoke it directly in a conversation, including through an @ mention or from the + menu where available. Availability can depend on your plan and workspace settings.

Are the Lara Translate integrations for Claude, Slack, and Make available yet?

Not yet. The ChatGPT plugin is published, and the Claude, Slack, and Make integrations are currently going through their respective marketplace review processes.

What is the Group Admin role, and how is it different from a Team Owner?

The Group Admin role, available for Team accounts, including Enterprise accounts that run on Team plans, lets a Team Owner delegate the day-to-day management of an individual Group to another person. A Team Owner owns and controls the entire Team account, while a Group Admin manages a single Group on the Owner’s behalf.

What is Generative Image Translation?

Generative Image Translation is a mode in the Lara Translate web app that recreates an image around the translated text, adapting typography, spacing, and layout for a natural result. You can choose it instead of Inpainting, which replaces the text while keeping most of the image unchanged, depending on the balance you want between cost, visual fidelity, and how much of the image is modified.

What is My Translations and where can I use it?

My Translations is a personal library where you can save text translations, including the source, the translated content, and your edits, then reopen, edit, or delete them later. It is available across the Lara Translate web app, iOS, and Android.

What is Meaning in Context?

Meaning in Context, available on iOS and Android, lets you view the meaning of an individual word directly within the text you are translating, with the explanation generated from the surrounding context. It is most useful for ambiguous words whose meaning depends on the sentence around them.

What is TBX support for Glossaries?

Lara Translate now supports TBX (TermBase eXchange) for Glossary import and export through the SDK, so you can move terminology databases in and out of Lara Translate without converting them to CSV first. Web app support is planned for the next few days.

Can Lara Translate handle EPUB files?

Yes. Document Translation supports EPUB files in the Lara Translate web app and through the SDK, so you can translate e-book and digital publishing content without converting it to an intermediate format first.

This article is about

• The Lara Translate plugin for ChatGPT, now published in the ChatGPT Plugins Directory
• Lara Translate integrations for Claude, Slack, and Make in marketplace review
• The new Group Admin role for Team and Enterprise accounts, and how it differs from a Team Owner
• My Translations, now live across the web app, iOS, and Android
• Generative Image Translation in the Lara Translate web app, alongside Inpainting mode
• Single Sign-On on iOS and Meaning in Context on iOS and Android
• Native TBX support for Glossaries and EPUB support through the SDK

L'articolo Lara Translate September 2026 Updates: Lara Translate in ChatGPT, Group Admins, and My Translations proviene da Blog | Lara Translate.

August 2026 puts most of its attention there. Team owners can now organize members into groups and share glossaries and translation memories with a whole team or a single group. On mobile, iOS gained translation memories and glossaries, and Alternative Translations arrived on both iOS and Android. On the developer side, Audio-to-Text translation is available through the API and SDKs, and Audio-to-Audio translation added voice cloning. And Lara for Zapier is now live in the Zapier marketplace.

Here are the Lara Translate August 2026 updates: what shipped, and why it matters for teams.

What’s new for teams: groups, shared glossaries and translation memories

When a whole organization works from one Lara Translate account, the marketing team’s glossary is not the legal team’s glossary, and an owner needs a way to keep those apart without spinning up a separate account for every department.

Team owners can now manage groups directly inside Lara Translate. From the group management area, you can add a group, rename it, or delete it. Members can be assigned to groups individually or in bulk, and invitation links can be configured so a new user joins a specific group as soon as they accept. A member belongs to one group at a time.

Groups now connect to Lara Translate’s linguistic resources too. Glossaries and translation memories can be shared through a Shared with picker at three levels: personal (just you), the entire team, or one or more specific groups. That gives each part of an organization control over which terminology and translation history it works from.

At the same time, team members can create their own personal glossaries and translation memories and rename the resources they own, so personal work stays separate from shared team assets. The translation interface was updated to make personal, team, and group resources easier to tell apart when you select them.

See the full guide to team groups and resource sharing.

What’s new on mobile: translation memories, glossaries, and Alternative Translations

The translation you do on your phone should not forget everything your account already knows. Until now, memories and glossaries lived on the web.

The iOS app now brings translation memories and glossaries into the mobile experience. You choose which memories and glossaries Lara should adapt to from the options menu, and the selection applies across Text, Documents, and Images. It is account-wide, matching the web app, so the resources you pick follow you across surfaces. A visual indicator on the control shows when memories or glossaries are active, and resources that are still importing or that failed to import are disabled and show their status. Creating and importing resources still happens in the web app for now, with a Manage action that opens the right web page from iOS.

Alternative Translations is now available on both iOS and Android. Tap ALT below a translated text to see alternative renderings for specific words or phrases, each with a short explanation of the context or register, then swap in the one that fits. It is a way to fine-tune wording without rewriting the sentence or starting the translation over.

Learn how to use translation memories and glossaries in the mobile app.

Get Lara Translate on your phone

Translation memories, glossaries, and Alternative Translations, now in your pocket.

Download for Android | Download for iOS

What’s new for developers: Audio-to-Text and voice cloning

Spoken content is hard to work with. A recorded interview or a voice note is not searchable, not translatable in place, and not something you can drop into a text pipeline without transcribing it first.

Audio-to-Text translation is now available through the Lara API and SDKs. Upload an audio file and get back both the original transcription and its translation as text, in a single workflow. Supported formats are .wav, .mp3, .opus, .ogg, and .webm, with 68 source languages for the audio and over 200 target languages for the translated text. Files can run up to 200 MB and two hours, and processing is asynchronous, which suits longer recordings and backend integrations. You can apply translation memories, glossaries, and a translation style (Faithful, Fluid, or Creative). Pricing is €0.05 / $0.05 per minute of audio. It fits use cases like subtitles, translated transcripts, meeting notes, media analysis, and accessibility.

Audio-to-Audio translation now supports voice cloning. Instead of recreating translated audio with a predefined target voice, Lara can analyze the acoustic profile of the source speaker, including timbre, pitch, and vocal nuance, and generate target-language audio that closely mimics their original voice. You turn it on with the voice_cloning parameter. It requires explicit opt-in and has its own pricing, and it is built for audio with one primary speaker, such as voiceovers, narrations, training material, and podcasts. This keeps speaker identity consistent across languages, which matters for multilingual media, training content, and presentations.

See the audio translation documentation for developers.

Is Lara Translate available on Zapier?

Yes. Lara for Zapier is approved and now live in the Zapier marketplace, so you can add translation to your workflows without building a custom integration.

The integration provides four actions: Translate Text, Upload Document for Translation, Get Document Status, and Download Translated Document. You can connect Lara Translate to the apps you already use, so a new file in a shared drive or a new row in a spreadsheet can trigger a translation and route the result wherever it needs to go. Translation memories, glossaries, and styles carry into those Zaps, so automated translations follow the same terminology as the rest of your work. Even with incognito mode.

Explore Lara Translate on Zapier.

What else is new in integrations: Wordscope and Langdock

Lara Translate is most useful where you already work. Two new integrations bring it into a professional CAT tool and into an AI workspace, so you do not have to switch apps to get context-aware translation.

Wordscope is a browser-based CAT tool for professional translators. With the new integration, Lara Translate works as a machine translation engine inside Wordscope, delivering suggestions directly in your translation projects. If you have an active Lara Translate subscription, you add Lara as a private engine in Wordscope under Settings, then Machine Translation, using your API credentials (the Access Key ID and Access Key Secret from My Account, API, Credentials). Once validated, Lara is available across all your Wordscope projects. See the Wordscope integration.

Langdock is an AI workspace where teams build agents and workflows. Through Lara Translate’s MCP server, those agents can call Lara’s translation tools directly, including language detection, translation, and memory management. You connect it from Langdock’s Integrations settings by adding the remote MCP server URL, authorizing with your Lara Translate credentials over OAuth, and enabling the tools you want. From there, translation becomes an action your agents can run inside a workflow. See the Langdock integration.

What to expect next

August’s shipped updates, team groups with shared glossaries and translation memories, mobile memories and glossaries on iOS, Alternative Translations on both mobile apps, Audio-to-Text through the API and SDKs, voice cloning for Audio-to-Audio, and Lara for Zapier, are built around one theme: making Lara Translate work for teams and for the tools teams already use.

A few more things are already moving. My Translations is rolling out as a dedicated area where you can save useful source and translated pairs, including your edits, and return to them later without repeating the work. And the Lara Translate plugins for Make and Slack have been submitted for review in their respective marketplaces. You can follow the full changelog on the What’s New page.

FAQ

How do team groups work in Lara Translate?

Team owners manage groups from a dedicated group management area inside Lara Translate. You can add, rename, and delete groups, assign members individually or in bulk, and configure invitation links so a new user joins a specific group when they accept. A member belongs to one group at a time.

Can I share a glossary or translation memory with only part of my team?

Yes. Glossaries and translation memories can be shared through a Shared with picker at three levels: personal (just you), the entire team, or one or more specific groups. This lets different departments work from their own terminology and translation history.

Can I use translation memories and glossaries in the Lara Translate mobile app?

On iOS, yes. You select which memories and glossaries Lara should adapt to from the options menu, and the selection applies across Text, Documents, and Images. It is account-wide and matches the web app. Creating and importing resources still happens in the web app for now, reachable through a Manage action from iOS.

What are Alternative Translations?

Alternative Translations, available on iOS and Android, let you tap ALT below a translated text to see alternative renderings for specific words or phrases, each with a short explanation of context or register, and swap in the one you prefer without rewriting the sentence.

What is the difference between Audio-to-Text and Audio-to-Audio translation?

Audio-to-Text returns written output: it transcribes spoken content and translates it into text. Audio-to-Audio produces a synthesized voice file in the target language. Audio-to-Text supports .wav, .mp3, .opus, .ogg, and .webm files up to 200 MB and two hours, with 68 source languages and over 200 target languages, priced at €0.05 / $0.05 per minute.

What is voice cloning in Audio-to-Audio translation?

Voice cloning lets Audio-to-Audio translation preserve the original speaker’s voice instead of using a predefined target voice. Lara analyzes the source speaker’s acoustic profile, including timbre, pitch, and vocal nuance, to generate target-language audio that mimics their voice. It is enabled with the voice_cloning parameter, requires opt-in, has its own pricing, and is built for audio with one primary speaker.

What can I do with Lara for Zapier?

Lara for Zapier, now live in the Zapier marketplace, offers four actions: Translate Text, Upload Document for Translation, Get Document Status, and Download Translated Document. You can connect Lara Translate to the apps you already use to automate translation inside existing workflows, and translation memories, glossaries, and styles carry through.

Which new integrations does Lara Translate support?

Two new integrations shipped alongside Zapier. Wordscope, a browser-based CAT tool, can now use Lara Translate as a private machine translation engine through your API credentials. Langdock, an AI workspace, can connect to Lara Translate’s MCP server so its agents call translation, language detection, and memory tools directly inside workflows.

This article is about

• Team groups in Lara Translate, with members assigned individually or in bulk and invitation links that join a specific group
• Sharing glossaries and translation memories with a whole team or one or more specific groups
• Translation memories and glossaries in the Lara Translate iOS app across Text, Documents, and Images
• Alternative Translations on iOS and Android
• Audio-to-Text translation through the Lara API and SDKs
• Voice cloning in Audio-to-Audio translation
• Lara for Zapier, now live in the Zapier marketplace
• New integrations with Wordscope (a browser-based CAT tool) and Langdock (an AI workspace, via MCP)

L'articolo Lara Translate August 2026 Updates: Team Collaboration, Shared Resources, and Voice Cloning proviene da Blog | Lara Translate.

Lara 3 represents a fundamental shift in how translation AI is built and delivered. Backed by our 27 years of experience in machine translation, the third generation of Lara moves beyond imitation-based training and introduces “learning by doing,” a training paradigm in which the model practices translation, receives feedback rooted in professional reviewer expertise, and refines its own output before ever serving a customer. According to blind human evaluations, the result is the largest quality leap ever observed between two Lara generations, achieved alongside dramatic improvements in speed and cost efficiency. The release also brings a broad set of new product capabilities, spanning image, audio, and document translation, and a redesigned pricing model built around transparency and organization-wide access.

From Imitation to Experience

The history of machine translation has unfolded through distinct technological eras. Rule-based systems, in which humans manually encoded linguistic rules, dominated from 1999 to 2005. In 2006, statistical machine translation marked the first breakthrough of machine learning in the field: rules were learned from data rather than written by hand. In 2014, sequence-to-sequence architectures brought neural networks to translation, and in 2017 the transformer, introduced in the landmark paper “Attention Is All You Need”, enabled models to leverage long context for dramatically better output. In 2022, the industry entered the era of LLM-based translation, specializing large language models for the translation task.

Every one of these generations, however, shared a common foundation: imitation. Models were shown a source sentence and a reference translation and trained to replicate that reference. The approach works, but it has an inherent ceiling. For any given sentence, multiple correct translations exist; training a model to match only one of them teaches it to reproduce a translation, not to understand why a translation is good. A model trained purely by imitation can, by definition, only be as good as its training data.

Lara 3 is designed to break that ceiling. Think of how humans learn: children learn first by imitation, then by pursuing goals set by parents and teachers, and finally, as adults, by self-judgment, evaluating their own work and improving without external instruction.

It is this final capacity, self-judgment, that Lara 3 introduces to machine translation.

How Learning by Doing Works

Imitation remains the foundation of training, but Lara 3 adds a final phase in which the model enters a virtual practicing environment.

Three things happen there. First, Lara explores: given a sentence, it produces multiple variations, experimenting with style, tone, and wording. Second, an automatic judge evaluates each attempt, identifying what works and what doesn’t, down to whether a specific word is correct in a specific context. Third, Lara refines: it incorporates that feedback into its learning, reinforcing hypotheses that score well and correcting those marked as errors. This cycle repeats millions of times, and it all happens during training; by the time Lara serves its first translation, the learning is already baked into the model.

The distinguishing element is the judge itself, the part that only we could build. Rather than scoring translations against abstract or generic evaluation metrics, it was created from the deep expertise of professional reviewers working on real translations. Their standards, their reasoning, and their corrections shape the feedback Lara practices against, the same type of feedback professional translators give in their day-to-day work. For enterprise teams, this means the model’s standards are effectively your standards.

Benchmark Performance

In blind human evaluations, Lara 3 tops the public WMT2025 benchmark, which covers books, news, and user conversation, edging out frontier models including Fable-5 and GPT-5.6 Sol and clearly surpassing Google and DeepL. Enterprise localization, however, is considerably harder than general-purpose translation: teams demand consistent brand voice, terminology and style guide compliance, product context, and content that feels native in every market. On a production benchmark built specifically for enterprise localization, Lara 3 leads in every domain tested (travel, technology, and finance) and in all 21 language pairs evaluated.

Quality is only one part of the production equation. Compared with Fable-5, Lara delivers the same workflow more than 23 times faster, a difference that makes real-time integration practical: product content, support experiences, and customer-facing journeys can be translated without noticeable delay. On cost, Lara provides almost four times more translation capacity than Fable-5 for the same budget, making it the most cost-efficient option among the competitors evaluated. Taken together, teams no longer need to trade off between quality, speed, and cost.

New Product Capabilities

Lara 3 ships with an extensive set of features, available immediately. Image translation preserves layout with striking fidelity; small text, angles, and shading are all localized, and is integrated into the mobile app, where you can photograph a restaurant menu or any document and receive a translated version.

Audio translation preserves the original speaker’s timbre while applying the same adaptive quality of Lara’s text engine, including translation memories, glossaries, and style guides.

For text workflows, you can now copy and paste rich content from any application and retain full formatting in the web interface.

Document translation, already supporting 72 file formats, sees a 70% reduction in layout errors, with automatic font resizing to keep layouts intact when translations run longer than the source.

A new browser extension brings website and in-browser translation to any environment.

Developers gain several additions: Lara Think, a reasoning mode that cuts errors nearly in half when higher quality is required; Lara Prosa, designed for literature and editorial content with long-context coherence and publication-specific style; multilingual profanity detection and filtering; and a command-line interface plus an MCP server that make Lara fully agentic, integrating with ChatGPT, Claude, and Groq.

Transparent, Flexible Pricing

Lara 3 abandons per-seat and per-token billing. Token-based pricing is inherently unpredictable: providers define what a token is, and reasoning models can generate 10 or 100 times more output than expected. Lara instead charges only for source characters; there are no charges for glossaries, context, translation memory, or instructions.

Your organization pre-purchases a character allowance shared by everyone: a single account can invite unlimited colleagues, with all features (text, documents, images, audio) billed against the same pool, and extra usage available on demand. If you know your volume, you know exactly what you will spend.

Privacy, Security, and Availability

Customers can balance data protection against model improvement through multiple privacy options, rely on certifications designed to satisfy InfoSec requirements, and choose data residency in the European Union or the United States. Lara 3 is available to selected partners today and will be publicly available in the coming weeks; product features can be explored now at laratranslate.com.

Frequently asked questions

What does “learning by doing” mean in Lara 3?

Learning by doing is a training method where Lara practices translation instead of only copying reference translations. During training, the model produces several versions of a sentence, an automatic judge scores each one against professional-reviewer standards, and Lara reinforces the strong choices while correcting the weak ones. This cycle repeats millions of times, and all of it happens during training, so the improvement is baked into the model rather than added at runtime. The goal is to teach Lara why a translation is good, not just how to reproduce one that already exists.

How is Lara 3 different from earlier versions of Lara?

Earlier generations, like every machine translation system before them, were trained purely by imitation, matching a source sentence to a single reference translation. Lara 3 keeps imitation as a foundation but adds a self-judgment phase where it evaluates and refines its own output. According to blind human evaluations, that produced the largest quality leap ever observed between two Lara generations. It also arrived alongside dramatic improvements in speed and cost efficiency, with the same workflow running more than 23 times faster than Fable-5.

How does Lara 3 perform against other translation models?

On the public WMT2025 benchmark, judged by blind human evaluation across books, news, and user conversation, Lara 3 finishes first, edging out frontier models including Fable-5 and GPT-5.6 Sol and clearly surpassing Google and DeepL. On a separate production benchmark built specifically for enterprise localization, it leads in every domain tested, travel, technology, and finance, across all 21 language pairs evaluated. Enterprise localization is a harder test because it demands consistent brand voice, terminology and style guide compliance, product context, and content that feels native in every market. Lara 3 was designed to hold up under exactly those demands.

How much does Lara 3 cost?

Lara 3 charges only for source characters and abandons both per-seat and per-token pricing. There are no charges for glossaries, context, translation memory, or instructions, which removes the unpredictability of token billing, where reasoning models can generate 10 or 100 times more output than expected. Your organization pre-purchases a character allowance shared by everyone, a single account can invite unlimited colleagues, and all features (text, documents, images, audio) are billed against the same pool, with extra usage available on demand. If you know your volume, you know exactly what you will spend.

When can I use Lara 3, and where is my data stored?

Lara 3 is available to selected partners today and will be publicly available in the coming weeks, and you can explore its product features now at laratranslate.com. On data, you can balance protection against model improvement through multiple privacy options and rely on certifications designed to satisfy InfoSec requirements. You can also choose data residency in the European Union or the United States. That combination is meant to satisfy both consumer and enterprise security expectations.

L'articolo Introducing Lara 3: Translation AI That Learns by Doing proviene da Blog | Lara Translate.

June 2026 rounds out several of these workflows at once. Audio-to-audio translation shipped in the web app. Image translation went live in production on iOS and Android. The Browser Extension reached Microsoft Edge. Lara CLI picked up translation memory and glossary management. And teams get a clearer view of how much of their shared character pool they’ve actually used. Two more pieces (a new image full rebuild mode and style guide management via API) are taking shape and worth flagging early.

Here are the Lara Translate June 2026 updates: what shipped, and what’s still on the way.

What’s new in the Lara Translate web app: audio-to-audio translation and usage visibility?

Audio-to-audio translation is now available directly from the web interface, no separate transcription tool required. Go to laratranslate.com, open the new Audio tab in the Translate section, and drag and drop a file – or browse to select one from your device. Choose the source and target languages and start the translation.

The Audio tab supports bulk file translation, so you can upload multiple files at once, and multi-language translation, so a single session can output several target languages together. Supported formats are .wav, .mp3, .opus, .ogg, and .webm. Audio translation draws from the same shared character pool as every other feature.

See the full guide to translating audio with Lara.

Speaking of that shared pool: team admins now get a clearer picture of how it’s being used, from two angles. First, by service: admins can see total consumption broken down by feature across the whole team, so it’s clear how much of the pool went to image, document, interpreter, or audio translation overall. Second, by member: admins can see each team member’s total consumption for the period.

What’s not available yet is the two combined: you can see what the team used per service, and you can see what each person used in total, but not which services a specific member used most. For teams on the shared character pool since May, this is the visibility that makes the model easy to manage day to day: no more wondering whether a number on the usage page is stale or accurate.

What’s new for image translation on iOS and Android?

Image translation is now in production on both the iOS and Android apps, extending Lara’s multimodal capabilities to the devices where images are actually captured, stored, and shared. Take a photo or choose one from your photo library, and Lara translates its content directly: signs, menus, screenshots, documents, and more, in a few taps.

Lara is also now integrated into the image sharing flow on both platforms, so you can send a photo straight to the app from Photos or your gallery without opening Lara first. This builds on April’s update, which added image files to the document picker; image translation is now a native, standalone capability rather than a document-mode workaround.

Get Lara Translate on Android.
Get Lara Translate on iOS.

Get Lara Translate on your phone

Translate images straight from your camera, photo library, and share sheet.

Download for Android | Download for iOS

Is the Lara Translate Browser Extension available for Microsoft Edge?

Yes – the Lara Translate Browser Extension is now listed on the Edge Add-ons marketplace, extending the extension beyond Chrome to anyone who uses Edge as their main browser.

The Edge version brings the same feature set as the Chrome sidebar: page translation, selected-text translation, free-form text input, and drag-and-drop document translation, all in one place. The marketplace listing itself has been localized in English, French, German, Italian, Russian, Spanish, and Swedish, with further alignment between the Chrome Web Store and Edge Add-ons listings planned as part of Lara’s broader localization strategy.

Get the Lara Translate Browser Extension for Microsoft Edge.

What’s new in Lara CLI?

Lara CLI now supports translation memory and glossary management directly from the command line, with interactive prompts and automatic lara.yaml syncing. Developers and localization teams can create and manage the resources that drive translation consistency (memories and glossaries) without leaving the terminal or switching to the web app.

Get started with Lara CLI.

What’s next for the Lara API: image full rebuild and style guides

Two developer-facing features are taking shape in the Lara API.

A new generative image full rebuild mode would add a fourth option to Lara’s Image API, alongside overlay, inpainting, and image-to-text: instead of placing translated text over the original or reworking it in place, this mode rebuilds the entire image, including the translated content, for the highest visual fidelity.

Style guide management is also becoming available through the API, as a progressive rollout. At this stage, it works as a container: the API can list, reference, and manage a style guide, but the content itself is still created by the Lara team on a per-request basis. If you’d like a style guide set up for your account, contact support@laratranslate.com.
We’ll share more details as both features move toward general availability.

What to expect next

June’s shipped updates – audio-to-audio translation, native mobile image translation, the Edge extension, Lara CLI’s memory and glossary tools, and clearer usage visibility – round out the workflows teams already rely on.

Two more things are already moving. A document translation update focused on formatting preservation has just been released and is currently in testing, aiming to keep layout and structure more intact across translated files. And a new feature is rolling out that lets you import and export Translation Memories directly from your account settings, instead of managing them elsewhere. Alongside these, the new image full rebuild mode and style guide management via API continue to take shape.

More updates are on the way. You can follow the full changelog on the What’s New page.

FAQ

What audio formats and usage limits apply to audio-to-audio translation?

The Audio tab in the web app accepts .wav, .mp3, .opus, .ogg, and .webm files. Usage is drawn from your shared character pool at a rate of 40 characters per second of audio – for example, a 15-second voice note costs 600 characters.

What can a team admin see about shared usage?

A team admin can see two views: total consumption broken down by service (image, document, interpreter, audio, and so on) across the whole team, and total consumption per individual team member. The two aren’t cross-referenced yet – an admin can’t currently see which services a specific member used most, only their overall total.

How is the new mobile image translation different from the file-picker support added in April?

April’s update added image files to the document picker on iOS and Android, so images were translated through the document workflow. June’s release makes image translation a native, standalone capability: you can translate directly from the camera, photo library, or share sheet, without routing through documents.

Does the Microsoft Edge extension have the same features as the Chrome version?

Yes. The Edge listing includes the same functionality as the Chrome sidebar – page translation, selected-text translation, free-form text input, and drag-and-drop document translation.

What can Lara CLI do with translation memories and glossaries?

Lara CLI now lets you manage translation memories and glossaries from the command line, with interactive prompts and automatic syncing to your lara.yaml configuration file.

Can I create a style guide today?

Style guide management is rolling out progressively. Right now it’s available as a container through the API, but the Lara team creates the content for you rather than it being fully self-serve. To have a style guide set up for your account, email support@laratranslate.com.

Is the new image full rebuild mode available yet?

Not yet on general release. It’s planned as a new mode in the Image API, alongside overlay, inpainting, and image-to-text, and will rebuild an entire image rather than editing it in place. Access model and timeline are still to be confirmed.

This article is about

• Audio-to-audio translation in the Lara Translate web app, plus clearer team usage visibility by service and by member on the shared character pool
• Image translation now in production on the Lara Translate iOS and Android apps, including camera and share sheet support
• The Lara Translate Browser Extension now available for Microsoft Edge
• Translation memory and glossary management added to Lara CLI
• A first look at the new image full rebuild mode and the progressive rollout of style guide management on the Lara API
• What’s coming next: improved document translation formatting preservation (in testing) and Translation Memory import/export directly in account settings

L'articolo Lara Translate June 2026 Updates: Audio Translation, Mobile Image Translation, and Edge Support proviene da Blog | Lara Translate.

Lara Translate is not waiting for the industry to catch up. Starting today, all team plans include unlimited users. You pay for translation volume, not for the number of people with access to the platform.

The SaaS Apocalypse: what it means and why translation is the clearest example

For years, enterprise software was sold seat by seat. The more people use the tool, the more you pay. That made sense when human labor was the multiplier.

AI changes that assumption everywhere it lands. When one person with the right AI tools can produce what three people did before, per-seat pricing stops reflecting value and starts penalizing efficiency. Analysts and operators have started calling this reckoning the SaaS Apocalypse (or SaaSpocalypse): the point where AI-driven productivity makes per-user licensing structurally indefensible.

Translation is the clearest case. A company can now give Lara Translate to its entire workforce: marketing, product, legal, sales, customer support, anyone who communicates across languages. A small team of specialists shifts from doing all the translation to doing what actually requires human judgment: reviewing high-stakes output, maintaining terminology, making calls on tone and cultural nuance. The AI handles the volume. The result is more languages, more people covered, at a fraction of the previous cost.

The problem with seat-based pricing when AI handles baseline translation

Seat-based licensing made sense when software required human labor to operate at a fixed ratio. You purchased accounting software, hired accountants, and the number of seats matched the size of the team. Output scaled linearly with headcount.

AI breaks that ratio.

Today, a company can roll out Lara Translate to its entire workforce. The localization team does not disappear: it shifts. Instead of translating everything themselves, three specialists focus on what actually requires human judgment: reviewing high-stakes output, maintaining terminology in glossaries and translation memories, and making calls on tone and cultural nuance. The AI handles the rest at scale.

Under seat-based pricing, this creates an absurd problem. You want to give access to 500 employees, but the model charges per head. So you either pay for 500 seats (most of which are used sporadically), or you restrict access and lose the productivity gain entirely. Meanwhile, your translation volume is growing, your team is shrinking, and the vendor’s response is to charge more per remaining seat. That is backwards.

Your pricing model should reward productivity, not punish it.

Translation volume is seasonal. Seat-based pricing is not.

Even without AI, seats were a poor proxy for translation workload. Here is what actual usage looks like for a mid-market team:

• February: 2 million characters. Routine product documentation updates, marketing assets, customer support content across languages.
• November: 9 million characters. Product launch across twelve languages. Localized landing pages. Legal contract translations. Investor materials. Three campaigns running simultaneously.

Most teams respond to that gap in one of three bad ways. They overpay for unused capacity ten months of the year. They hit November unprepared and delay launches or cut languages. Or they purchase temporary seats at full monthly cost for contractors who only need access for six weeks.

None of those are good outcomes. Consumption-based pricing solves all three.

What changed and how the new model works

Lara Translate Team plans now work like this.

You select a baseline plan that matches your typical monthly volume. That plan includes unlimited users: your full-time team, contractors, reviewers, project managers, anyone who needs access. No seat management, no license juggling, no deciding who gets in and who doesn’t.

When your November spike hits and volume reaches 9 million characters, you keep working. The extra usage is billed at a simple per-character rate. When December drops back to baseline, your bill reflects that. This is not revolutionary — it is how cloud infrastructure has worked for years. It is how API-based AI tools already work. It is the model that makes sense when the link between users and output is no longer fixed.

A concrete example: before and after

Take a mid-market SaaS company with operations across twelve languages. They have rolled out Lara Translate company-wide — marketing, product, legal, sales, all using it daily. A three-person localization team manages quality: maintaining glossaries, reviewing high-stakes translations, and handling anything that needs a specialist eye. The AI handles the rest. Their typical monthly volume is around 3 million characters.

Under the old seat-based model, giving access to the entire company meant buying seats for everyone. 200 employees with occasional translation needs, 50 regular users, a handful of contractors in Q4 — each one a line item at full monthly rate, whether they translated once a week or once a quarter.

Under consumption-based pricing, they are on the 3M characters/month baseline plan. The entire company has unlimited access at no extra cost per person. During Q4, a product launch across all languages pushes volume to 9 million characters — 6 million over the baseline. At €20 per additional million characters, that is €120 extra for that month. In January, when volume drops back to 2 million characters, they are under their plan and the bill reflects it.

Same team. More languages. Lower overhead. No seat math.

What this means in practice for your team

If you manage a team that works across languages (whether that’s a marketing department, a product team, a legal function, or a company-wide productivity rollout), the practical shift is direct.

Add everyone who needs access: full-time staff, contractors, reviewers, project managers, and executives who occasionally need a quick translation. No cost per person. Lara Translate’s glossaries and translation memories work consistently for every user, so quality and brand consistency stay controlled regardless of how many people are on the account.

Stop managing licenses. No more deciding who gets a seat. No more compliance headaches from shared credentials. No more purchasing temporary seats at monthly rates for short-term contractors.

Pay for what you use. Quiet months cost less. Busy months cost more. Seasonal spikes stop forcing bad trade-offs between budget and delivery.

How to get started with the new pricing

If you are currently on a seat-based Lara Translate plan, your subscription has transitioned automatically today. Log into your account dashboard to review your new baseline quota and add users.

If you are evaluating translation platforms and seat-based pricing has been a friction point, this removes it. Bring your whole team on day one: your glossaries, translation memories, and Incognito Mode settings all apply across every user from the start.

Translation will not be the last software category to move to consumption-based pricing. The vendors that align their model with how work actually happens will have a durable advantage. Lara Translate is making that move now, so your team doesn’t have to wait.

Full pricing details are at laratranslate.com/pricing.

FAQs

What is the SaaS Apocalypse and why does it affect translation software?

The SaaS Apocalypse refers to the structural disruption AI is causing to per-seat software pricing. When AI allows one person to produce what previously required three, charging by headcount no longer reflects value. Translation is one of the first categories where this has become undeniable — AI handles the volume, specialists handle quality, and the team size no longer determines output. Consumption-based pricing is the direct response: pay for the work done, not the people who could do it.

What is consumption-based pricing for translation software?

Consumption-based pricing means you pay for the volume of translation work performed — typically measured in characters — rather than for the number of users who have access to the platform. Your team size does not affect your cost. Your translation output does.

Does my existing Lara Translate plan change automatically?

Yes. If you are currently on a seat-based plan, it has transitioned automatically. Your baseline quota reflects your previous usage tier. Log into your account dashboard to review the details and add any additional team members.

How does Lara Translate handle seasonal spikes in translation volume?

When your monthly usage exceeds your baseline plan, the extra volume is billed at a per-character rate. There is no cap, no block, and no requirement to upgrade your plan mid-month. After the spike, billing returns to your baseline rate.

Can I add contractors and freelancers without extra cost?

Yes. All team plans include unlimited users. You can add contractors, reviewers, or external collaborators at no additional per-seat charge. They get access to your shared glossaries and translation memories from the moment they join.

How does this pricing compare to per-seat translation tools?

Per-seat tools charge a fixed monthly rate per user regardless of how much translation work each user performs. Consumption-based pricing charges for actual output. For teams with seasonal spikes, contractors, or AI-assisted workflows where fewer people produce more volume, consumption-based pricing typically costs less and scales more predictably.

What features are included on all team plans?

All team plans include glossaries, translation memories, Incognito Mode, support for 70+ file formats (including XLIFF, PO, and SRT), and access to Lara Translate’s API. Unlimited users are included at every tier.

L'articolo Lara Translate Drops Seat-Based Pricing: Here is why proviene da Blog | Lara Translate.

Managing glossaries without API access. Profanity slipping through multilingual pipelines. Formatting that disappears on translation.

These aren’t edge cases — they’re the everyday friction that slows localization teams down. April 2026 is the month Lara Translate addressed most of them at once. Eight updates shipped across the web app, browser extension, integrations, and developer tooling. These are the Lara Translate April 2026 updates, maintained by the Lara team at Translated.

April’s theme is breadth without fragmentation. The updates touch almost every surface of the product — web app, browser extension, integrations, developer tooling — but each one addresses a specific, concrete friction point. Glossary management opens up to non-technical users. The Interpreter becomes more flexible. The CLI becomes more reliable. And across the board, the product gets closer to the standard enterprise teams expect.

What are the April 2026 updates?

These April 2026 release notes cover eight updates: the Browser Extension major release, Lara for Google Sheets defaults and preferences, Multidirectional Glossary CSV Import and Export in the web app, the More Tools tab, the Rich Text Toggle in Lara Text, Interpreter Voice Selection, Profanity Detection and Filtering, and Lara CLI v1.3.2. Some expand access to capabilities that previously required API or engineering involvement. Others improve reliability and control in workflows that already existed. A few do both.

What’s new in the Lara Browser Extension?

A major update to the Lara Browser Extension is now live, focused on translation quality and technical robustness across real web pages.

Web pages are messy. Non-standard layouts, complex content structures, dynamic content — these are the conditions the extension has to work in, not clean test cases. This release addresses the quality and stability gaps that show up in those real-world conditions.

• Improved page translation quality across a broader range of web content.
• Better handling of complex content structures, so pages with non-standard layouts translate more reliably.
• Increased performance and stability across typical browsing sessions.

Check out the browser extension here.

Can I set default preferences in Lara for Google Sheets?

The latest Lara for Google Sheets update lets users configure default translation styles, glossaries, and translation memories directly from the side panel.

Before this update, you had to specify settings manually on every LARATRANSLATE function call. For teams running product catalogs, localization reviews, or content audits in Google Sheets, that adds up fast. Now your preferences are set once and applied automatically.

• Set default translation styles, glossaries, and translation memories from the side panel — applied automatically to every LARATRANSLATE function call.
• Incognito mode controls are now available, giving users explicit control over whether translation data is retained.
• Support for team-level preferences, so shared spreadsheets use consistent settings across everyone on the integration.

Read more about the new Google Sheet Add-on.

Can I now import and export multidirectional glossaries in the web app?

Multidirectional glossaries now support CSV import and export directly in the Lara web app, with no API access required.

Previously, multidirectional glossaries were only manageable via API or SDK. That meant localization managers, editors, and content leads had to route every terminology update through an engineer. This update removes that dependency entirely.

• Import multidirectional glossaries via CSV directly from the web app — no API access or engineering involvement required.
• Export glossaries in CSV format for backup, editing in a spreadsheet, or sharing across teams.
• Aligns the web experience with developer capabilities, so terminology management is accessible to everyone on your team.
• Works alongside the existing MCP Glossary Management toolkit introduced in March, giving teams full flexibility: manage glossaries from the web app or directly from your AI development environment.

For localization and content teams who maintain brand terminology across projects, this closes the gap between what developers could do and what everyone else could do. That gap was always friction. Now it isn’t.

Find out more about Multidirectional Glossaries.
Read the technical documentation.

What is the More Tools tab?

The More Tools tab is now fully available, surfacing the broader Lara ecosystem directly inside the app.

Until now, discovering connected tools and integrations meant leaving the main experience and searching elsewhere. The More Tools tab changes that: everything in the Lara ecosystem is one click away, without breaking your workflow.

• Makes the full Lara ecosystem discoverable in one place, with no need to visit separate pages or navigate away from the app.
• New integrations will be added in the upcoming release, further expanding what’s accessible from within Lara.
• Reduces switching friction for teams that use multiple Lara-connected products as part of their daily workflow.

What is the Rich Text Toggle in Lara Text?

A new toggle in the Lara text editor lets users explicitly enable or disable rich text handling when working with formatted content.

Previously, rich text processing happened in the background without user control. If you pasted formatted content, Lara made a decision for you. Now you make that decision yourself, which matters when source formatting should or shouldn’t carry through to the output.

• Enable or disable rich text handling directly in the editor, depending on the content you’re working with.
• A contextual tooltip appears the first time you paste rich text, explaining the feature for new users without getting in the way of experienced ones.
• Gives translators and editors explicit control over formatting behavior — particularly useful for content that carries structural markup the translation should preserve or strip.

Find out more here.

Can I select and preview voices in the Interpreter?

The Interpreter now lets users select from multiple voices directly in the interface and preview each one before starting a session.

The right voice for a boardroom presentation is not the same as the right voice for a customer support call. Previously, you couldn’t test that difference before committing. Now you can.

• Browse available voices and choose the one that fits your context before a session begins.
• Preview mode lets you hear how each voice sounds, so there are no surprises once interpretation starts.
• Makes the Interpreter experience more adaptable across use cases — formal meetings, training sessions, live support, and more.

Discover voice selection for the Interpreter.

What is Lara’s new Profanity Detection and Filtering system?

Profanity detection and filtering is now fully available in production, integrated into Lara’s translation pipeline and available as a standalone API for independent content analysis.

For content platforms handling user-generated text in multiple languages, this kind of tooling has historically required a separate vendor and a separate integration. It’s now built into Lara. That’s worth pausing on.

Within the translate text endpoint:

• Identifies offensive language in both the source text and the generated translation.
• Configurable handling modes, depending on your workflow requirements: flag for review, mask with symbols, or block the profanity entirely (eg, replacing the profanity with a non-profanity that carries the same meaning).
• Available for all SDK-supported programming languages, with Ruby and Go support releasing in the coming days.

As a standalone service:

• A dedicated profanity detection API is available for analyzing text without performing translation.
• Enables integration into moderation, compliance, and content analysis pipelines that operate independently of translation workflows.

Check out our documentation for the Profanity Detection.

What’s new in Lara CLI v1.3.2?

Lara CLI v1.3.2 delivers a set of reliability and flexibility improvements for developer workflows, with the lock file corruption fix being the most significant change.

If you run Lara CLI in CI/CD pipelines or automation workflows, you’ve likely run into interrupted runs before. Previously, an interruption had the potential to corrupt the lara.lock file, requiring manual intervention to recover state. That risk is now addressed.

• Improved format and reliability of the lara.lock file
• Fix for corruption issues caused by interrupted runs
• Fixes to translation text formatting
• Support for batch key translation
• Introduction of “no trace” mode
• Additional minor bug fixes

Read more about Lara CLI.

What’s next for Lara Translate?

April’s direction reinforces a consistent pattern: Lara Translate is expanding access to capabilities previously limited to technical users, improving the surfaces teams interact with most, and tightening reliability at the infrastructure level. You can follow future updates on the What’s New page and start testing these features in your workflows today.

FAQ

What are the April 2026 updates in Lara Translate?

April 2026 brought eight updates to Lara Translate, spanning the web app, browser extension, integrations, and developer tooling. The browser extension received a major quality and stability release, and Lara for Google Sheets gained default preferences so teams no longer need to configure every function call manually. In the web app, multidirectional glossary CSV import and export is now available without API access, a More Tools tab surfaces the full Lara ecosystem in one place, and a Rich Text Toggle gives translators explicit control over formatting. The Interpreter added voice selection with preview, the profanity detection and filtering system moved to production as both an integrated endpoint and a standalone API, and Lara CLI v1.3.2 addressed lock file reliability and added batch key translation support.

What changed in the Lara Browser Extension?

The major update released in April improved page translation quality across a broader range of web content, added better handling of complex content structures so non-standard page layouts translate more reliably, and increased performance and stability across typical browsing sessions. Real web pages are messier than test cases — the update targets the quality and reliability gaps that appear in those real-world conditions specifically. A further update focused on UX improvements and document translation support inside the extension is planned before mid-May, so this release should be understood as foundational work rather than a final state.

What can I configure in Lara for Google Sheets?

You can now set default translation styles, glossaries, and translation memories directly from the side panel — these preferences are automatically applied to every LARATRANSLATE function call without requiring manual parameters each time. The update also adds incognito mode controls, giving users explicit control over whether translation data is retained during a session. Team-level preference support means shared spreadsheets use consistent settings across everyone on the integration, which matters for teams running product catalogs, localization reviews, or content audits at scale. Previously, every function call required manual configuration. That overhead is now gone.

Can non-technical users now manage multidirectional glossaries in Lara?

Yes. Multidirectional glossaries previously required API or SDK access, meaning every terminology update had to go through an engineer. As of April 2026, you can import and export them via CSV directly from the Lara web app — no engineering involvement required. This brings glossary management in line with what localization managers, editors, and content leads can do independently. It also works alongside the MCP Glossary Management toolkit introduced in March, so teams that prefer to manage glossaries from an AI development environment still can. The two approaches complement each other rather than replacing one another.

How does Profanity Detection and Filtering work in Lara?

Lara’s profanity detection and filtering system works in two modes. Integrated into the translate text endpoint, it identifies offensive language in both source text and translation output, with three configurable handling options: flag the content for review, mask it with symbols, or block the translation entirely. As a standalone API, it analyses text for profanity without performing translation, making it suitable for content moderation and compliance pipelines that operate independently of translation workflows. Both modes are available for all SDK-supported programming languages, with Ruby and Go support releasing shortly. For teams handling user-generated content in multiple languages, this removes the need for a separate moderation vendor.

Can I select and preview interpreter voices in Lara?

Yes. The Interpreter now lets you select from multiple voices directly in the interface and preview each voice before starting a session. This matters because the appropriate voice varies significantly by context: a formal boardroom presentation calls for a different register than a customer support interaction or a training session. The preview mode eliminates guesswork — you hear exactly how each voice sounds before committing, so there are no surprises once interpretation starts. Voice selection is available directly in the Interpreter interface without requiring any additional configuration.

What’s in Lara CLI v1.3.2?

Lara CLI v1.3.2 includes improved lara.lock file format and reliability, a fix for state corruption caused by interrupted runs, translation text formatting fixes, batch key translation support, “no trace” mode, and additional bug fixes. The lock file corruption fix is the most operationally significant change for teams running Lara CLI in CI/CD pipelines or automation workflows: previously, an interrupted run could corrupt state and require manual recovery. That risk is now addressed. Batch key translation support and “no trace” mode add flexibility for workflows that require either bulk processing or reduced logging footprint.

This article is about:

• Breaking down Lara Translate’s April 2026 updates, ordered by product area.
• Covering the browser extension major release and how it improves translation quality across real web pages.
• Explaining how Lara for Google Sheets defaults and preferences simplify translation workflows for spreadsheet-based teams.
• Explaining how multidirectional glossary CSV import and export in the web app extends terminology management to non-technical users.
• Covering the More Tools tab and Rich Text Toggle in the Lara text editor.
• Showing how Interpreter voice selection improves usability across use cases.
• Summarising the Profanity Detection and Filtering system — both integrated and standalone — now in production.
• Covering Lara CLI v1.3.2 reliability improvements.

Useful links and articles:

• Lara Translate web app
• Lara Translate Developer Docs
• Getting started with the Lara Translate MCP Server
• Lara Translate MCP Server (Help Center)
• Lara MCP Server on GitHub (open source)
• Lara Translate pricing
• What’s New: Lara Translate changelog

L'articolo Lara Translate April 2026 Updates: Browser Extension, Google Sheets & More proviene da Blog | Lara Translate.

Lara Translate for Google Sheets now lets you control exactly this. The updated add-on ships with a new sidebar for connecting your Translation Memories and Glossaries directly from your Lara account, plus three new formula parameters that let you override global settings on a per-cell basis. Here is what changed and how to use it.

What changed: the new sidebar

The Lara Translate sidebar now has two dedicated panels: one for Translation Memories and one for Glossaries. Both pull directly from your Lara account. Hit the refresh icon in either panel to sync the latest versions of your assets without leaving the spreadsheet.

What you select in the sidebar becomes the global default for all LARATRANSLATE calls in the sheet. That is the right setup for most use cases: pick your glossary once, it applies everywhere. But when a cell needs different handling, the formula parameters override the global setting. More on that below.

What changed: three new formula parameters

The full LARATRANSLATE formula now looks like this:

The three new optional parameters are:

• memories — one or more Translation Memory IDs from your Lara account
• glossaries — one or more Glossary IDs from your Lara account
• style — translation style: "faithful", "fluid", or "creative"

Any value passed in these parameters overrides the global sidebar setting for that specific cell. Everything else in the sheet is unaffected.

Three real scenarios where this matters

1. Product catalog with brand terms in one column, legal copy in another

You are localizing a product catalog. Column B contains product names and feature descriptions that must use your brand glossary. Column D contains regulatory disclaimers that need to be translated faithfully, word-for-word, with no creative license. Column F has short marketing taglines that should read naturally in the target language.

In Column B, the formula uses your brand glossary:

In Column D, no glossary, faithful style:

In Column F, creative style for the taglines:

Three columns, three different behaviours. One sheet. No manual switching.

2. Localization tracker for a software product

Your sheet tracks UI strings: button labels, error messages, onboarding copy, and in-app tooltips. Button labels and error messages need to match the approved UI glossary exactly. Onboarding copy should read naturally. Tooltips can be more flexible.

The approved UI glossary applies globally via the sidebar. For the onboarding rows, you add "fluid" as the style parameter. For tooltip rows that are going to a market without an approved memory yet, you pass a different memory ID in the formula. The rest of the sheet stays on the global setting.

Result: one sheet, one translation run, and every row gets the right controls applied automatically.

3. Multilingual content review with LARAEVAL

You receive translated content from an external vendor and need to quality-check it before publishing. Column A has the English source. Column B has the vendor translations. You add Column C with:

Lara scores each row from 1 to 3: 1 means major errors (missing content, wrong meaning, tone problems), 2 means minor or stylistic issues, 3 means the translation is good. You filter for rows scoring 1 or 2 and send only those back for revision. The rows scoring 3 go straight to publishing.

What used to be a manual spot-check across dozens of rows becomes a one-column formula run in seconds.

How to get started

If you do not have the add-on yet, install it from the Google Workspace Marketplace. You need an active Lara Translate Pro or Team plan to use the translation and evaluation functions.

Once installed, open it from Extensions > Lara Translate > Open. Sign in to your Lara account if prompted. The sidebar gives you the Translation Memory and Glossary panels. Sync your assets using the refresh icon in each panel, select what you want to apply globally, and you are ready to use LARATRANSLATE in any cell.

The full syntax reference, parameter details, and pricing are on the Lara Translate for Sheets support page.

Pricing reference

FAQs

Do the new formula parameters override the sidebar settings?

Yes. Any value you pass in the memories, glossaries, or style parameters of the LARATRANSLATE formula overrides the global setting configured in the sidebar for that specific cell. Cells without those parameters in the formula continue to use the sidebar’s global settings. This means you can mix global and per-cell configurations in the same sheet without conflict.

How do I find my Translation Memory and Glossary IDs?

The easiest way is to sync them via the sidebar. Open Extensions > Lara Translate > Open, then use the refresh icon in the Translation Memories or Glossaries panel. Your Lara account assets will appear and you can select them. If you need the IDs directly for use in formulas, they are available in your Lara account settings. The support page has the full reference.

Can I share the sheet with teammates and have them use their own Lara accounts?

Yes. If you share the sheet with someone who has editing access, any LARATRANSLATE or LARAEVAL function they trigger will consume characters from their own Lara account, not yours. This means each team member needs their own active Pro or Team plan to use the functions. It also means you are not charged for translations your teammates run.

Does LARAEVAL use my glossaries or translation memory when scoring?

No. LARAEVAL evaluates based on the source and target text only. Translation Memories, Glossaries, context, and style are not taken into account during evaluation. The score reflects the quality of the translation as written, independent of your terminology assets. If you want to check whether a translation respects your glossary, you need to do that as a separate review step.

This article covers

• What is new in Lara Translate for Google Sheets: the updated sidebar with dedicated Translation Memory and Glossary panels, and three new formula parameters
• How per-cell control works with the new memories, glossaries, and style parameters in LARATRANSLATE
• Three real use cases where different columns or rows need different terminology controls and translation styles in the same sheet
• How to get started with the add-on, including setup steps and a pricing reference for Pro and Team plans

Useful articles

• How to use the Lara Translate app in Google Sheets: full documentation
• How glossaries work in Lara Translate
• Translation styles: Faithful, Fluid, Creative

L'articolo Lara Translate for Google Sheets: Glossaries, Translation Memory, and Per-Cell Control proviene da Blog | Lara Translate.