FlorianEagox/WeeaBlind

A program to dub non-english media with modern AI speech synthesis, diarization, and voice cloning!

33
/ 100
Emerging

Combines FFmpeg, Coqui TTS, pyannote.audio speaker diarization, and SpeechBrain language identification to automatically analyze and synthesize dubbed audio matched to source timing, speaking rate, and volume. Supports granular control including selective dubbing of foreign-language subtitles only, multi-speaker voice assignment, vocal isolation for background music retention, and both system voices and AI-powered TTS models (VCTK/VITS preferred for speed). Designed as a Python application targeting Linux and Windows with optional GPU acceleration via CUDA for improved TTS and diarization performance.

323 stars. No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

323

Forks

31

Language

Python

License

Last pushed

Nov 21, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/FlorianEagox/WeeaBlind"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.