Now Supporting More Languages for Audio Processing
We expanded language support across upload, transcription, sentence segmentation, and alignment so multilingual workflows stay in one pipeline.
What You'll Learn
- What changed in the product this release
- How updates impact your day-to-day workflow
- Which improvements are shipping next
What shipped
We added first-class multilingual support to the core processing pipeline. You can now pick a language during upload and pass that context through transcription, sentence segmentation, and alignment.
Supported languages
- Spanish
- English
- French
- German
- Italian
- Portuguese
- Japanese
- Chinese
- Korean
Why this matters
In the previous setup, users had to rely on a single language default. With this release, language selection is explicit and carried through the full processing path, which improves transcription quality and alignment consistency for multilingual users.
Workflow changes
- Added language selection in upload before queueing jobs.
- Transcription now uses the selected language context.
- Sentence segmentation and alignment now map to language-aware settings.
- Added safe fallbacks so unsupported language-specific NLP models still process cleanly.
What's next
We'll keep expanding language coverage and add more language-specific quality tuning based on user workflows.
Try this update in your own workflow
Upload audio and use the latest features now
Go from upload to segmented export with the newest improvements enabled.