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.
Also shipped#
- Glossary retrieval is faster on every request. Glossary item embeddings switched to a smaller index – same recall, lower latency at inference time.
- Model fallback now triggers on parse error. If a model returns malformed JSON, localize moves to the next model in the chain instead of surfacing the error.
- Reference shots disabled on oversized payloads. Prevents 500s on jobs that exceed the model's context budget.