Conversation
- Add `TRANSCRIPTION_BACKEND` env var to switch between 'whisper' (default) and 'voxtral'. - Implement Voxtral transcription using OpenAI-compatible API. - Update `requirements.txt` and `pyproject.toml` with `openai` and audio libs. - Update README with setup instructions.
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
- Update `cli.py` to support `TRANSCRIPTION_BACKEND` env var. - Implement background thread for periodic transcription (simulated streaming). - Implement diff-based text updating (backspacing) for real-time feedback. - Add `text_lock` for thread safety. - Update `requirements.txt` and `pyproject.toml`. - Update README with Voxtral setup instructions.
1 participant
This PR adds the capability to use the Mistral Voxtral Realtime model for transcription.
It introduces a new environment variable
TRANSCRIPTION_BACKENDwhich defaults towhisperto maintain existing behavior.When set to
voxtral, the application connects to a local (or remote) Voxtral server (running via vLLM) using the OpenAI client.Dependencies were updated to include
openai,soundfile,librosa, andsoxr.README is updated with setup instructions for Voxtral.
PR created automatically by Jules for task 14670574883794321087 started by @mpaepper