James Pine f77dd621e2 feat: add CosyVoice2/3 TTS engine with instruct and voice cloning ...

Integrate Alibaba's CosyVoice2-0.5B and Fun-CosyVoice3-0.5B as a new
TTS engine supporting 9 languages, zero-shot voice cloning, and instruct
control (emotions, speed, volume, dialects).

The CosyVoice source is cloned at setup time into backend/vendors/ since
no PyPI package exists. A modelscope→HuggingFace shim redirects model
downloads to the public HF repos, and a lightweight pylogger shim avoids
pulling in pytorch-lightning as a transitive dependency.

Backend: cosyvoice_backend.py, __init__.py registry, models.py regex
Frontend: engine selector, language map, Zod schema, model descriptions
Infra: requirements.txt, justfile, release.yml, Dockerfile, PyInstaller

2026-03-17 12:31:20 -07:00

..

assets

Update date formatting logic and replace binary assets

2026-01-26 01:10:22 -08:00

workflows

feat: add CosyVoice2/3 TTS engine with instruct and voice cloning

2026-03-17 12:31:20 -07:00