Starstruk Logo MarkStarstruk

0.2.13

QuentinFuxa/WhisperLiveKit0.2.13Oct 30, 2025by QuentinFuxa

AI Summary

Major release separating translation engine into dedicated NLLW package, adding Silero VAD v6 support, and expanding model format support.

Key Highlights

  • --model-path supports PyTorch files or folders
  • Optimized SimulStreaming encoders (mlx-whisper, faster-whisper) supported
  • Voice Activity Detection based on Silero VAD v6
  • Translation engine separated into dedicated NLLW package
  • NLLW 0.1.0 backend for translation

New Features

  • PyTorch file/folder support for model-path
  • mlx-whisper and faster-whisper encoder support
  • Silero VAD v6 for voice activity detection
  • NLLW package separation for translation engine

Full Release Notes

## New Features

* `--model-path` can now point to either a PyTorch file or a folder. Optimized SimulStreaming encoders, `mlx-whisper` and `faster-whisper`, are now supported. See [Models Compatible Formats](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/docs/models_compatible_formats.md).
* Voice Activity Detection is now based on Silero VAD v6. Support for the `.onnx` format is coming soon.
* The simultaneous translation engine backend has been separated into a dedicated [NLLW](https://github.com/QuentinFuxa/NoLanguageLeftWaiting) package, allowing faster development. The current version is 0.1.0, with new releases expected more frequently than WhisperLiveKit updates. WhisperLiveKit 0.1.13 with NLLW 0.1.0 backend performs better than WhisperLiveKit 0.1.12, but is still unstable. Installation using `pip install whisperlivekit[translation]`  now installs nllw backend.
* [API changes](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/docs/API.md) are still in development. The core is evolving to enable a smoother transition.

## Bug Fixes

* Fixed UTF-8 character corruption in the SimulStreaming backend ([issue #261](https://github.com/QuentinFuxa/WhisperLiveKit/issues/261)).
* Fixed translation issues [#257](https://github.com/QuentinFuxa/WhisperLiveKit/issues/257) and [#258](https://github.com/QuentinFuxa/WhisperLiveKit/issues/258).

**Thank you to all contributors and community members who reported issues and provided valuable feedback.**