Human-in-the-loop for in-house AI translation review.

The async localization pipeline includes human-in-the-loop review an optional stage where the job pauses until a human edits or approves the AI translation. Until now, that stage routed to an external network of professional translators. Now you can set the review provider to Internal reviewers on an engine, and pending translations land in a review queue inside the dashboard instead of leaving your organization.

Lingo.dev v1.0 introduces localization engines  stateful translation APIs that you configure once and call from backend code, MCP, or CI/CD. Before today, every team that wanted consistent terminology, on-brand tone, and per-locale rules wired it up by hand: a glossary in one repo, brand-voice notes in a Notion doc, prompt scaffolding hard-coded into the app. The engine collapses all of that into a single addressable thing.

What's in the launch

• Localization engines. Configure models, brand voice, instructions, and glossaries per locale.

• LLM models. Pick the model per locale, with ranked fallback chains for reliability.

• Brand voices. Linguistic rules and tone per locale.

• Instructions. Per-locale translation rules for specific patterns.

• Glossaries. Lock down product terminology across languages and builds.

• AI Reviewers. Cross-model evaluation criteria for translation quality.

• Playground. Test engine configurations before they go live.

• Reports. Word generations, token consumption, top locales, glossary coverage, change rates.

RBAC is now available. Define roles, assign them to users, and grant per-engine access independently. Ownership transfer is supported, so the original creator is no longer a permanent dependency.

Also shipped

• Claude Desktop logs into your MCP server with a click. The server now speaks browser-redirect OAuth the client opens a tab, you confirm in the dashboard, you're in. No more copy/pasting API keys into client configs.

• lockedKeys on the async API. Slugs, IDs, URL parameters, and any value that's structural metadata rather than translatable content stay verbatim across target locales and bypass the LLM entirely.

• Logs show the context that produced each translation. Open any request in the Log tab and you can see exactly which glossary terms, instructions, and brand-voice rules the engine retrieved plus the glossary review reasoning.

• Cost-by-model breakdown. See how much you spent on each model, in tokens and in dollars.

Full changelog: lingo.dev/changelog

Auto top-up replenishes your credit balance automatically. Opt in once, set a threshold and an amount, and credits get purchased the moment your balance dips below the threshold translation CI runs stop failing on empty balances.

Also shipped

• New Reports charts: instruction adherence and terminology coverage. Track over time how often translations follow your configured instructions and apply your glossary terms.

• Credit balance alerts. Dashboard indicator shows current balance; emails fire at 20% remaining and at $0.

• ISO 5060 classification visible in triage. Each triaged job surfaces the standardized error class alongside the agent's suggestions.

The triage workflow reads any Jira ticket about a bad translation, looks at the offending output, and proposes the actual fix in the engine config: a glossary item to add, an instruction to tighten, a model config to adjust. Review the suggestion, accept or edit it, and the engine is fixed for every future translation not just the one that was reported.

Also shipped

• AI Reviewers now receive the same context the localizer saw. Brand voice, instructions, and glossary items reach the reviewer prompt, so scoring aligns with the engine's actual configuration instead of evaluating in a vacuum.

• Review filters in translation logs. Filter the translation logs by reviewer and score threshold e.g. any reviewer below 80%, or a specific reviewer below a given percentage.

The async localization API fans out a single localization request across every target locale in one POST and delivers results via webhook. Source payload in, job IDs out, webhook fires per locale as each finishes.

Also shipped

• Glossary CSV upload. Bulk-import glossary items from CSV with conflict resolution on collision, so re-imports don't duplicate entries.

• Jira and GitHub now connect over OAuth. Both integrations switched off API-token setup.

The Localization Jobs UI lands end-to-end. Inspect job groups, watch per-language progress, see the source payload, see the webhook delivery, drill into any failed locale. The async localization API ships jobs in parallel across every target locale, retries on failure, and webhooks back when done now you can watch it happen instead of reconstructing from logs.

Full changelog: lingo.dev/changelog

Engine provisioning is an async API that takes a fresh engine plus a few URLs or content samples and auto-configures the brand voice, glossary, and instructions for you. Multi-step manual engine setup collapses into one call.

Full changelog: lingo.dev/changelog

Today, we're introducing Lingo.dev Compiler: an npm library, that lets you build multilingual React apps without having to rewrite the existing React code.

It doesn't require extracting i18n keys, or wrapping text in tags. 100% free and open-source.