Softcatala/open-dubbing
Open dubbing is an AI dubbing system which uses machine learning models to automatically translate and synchronize audio dialogue into different languages.
The pipeline chains Whisper for automatic source language detection, pluggable translation engines (Meta NLLB, Apertium), and multiple TTS backends (Coqui, MMS, Edge, OpenAI) with speaker diarization via pyannote for gender-aware voice assignment. Runs entirely locally with open-source models, offers post-editing workflows through JSON metadata files to refine translations and voice parameters before re-rendering, and supports 100+ language combinations depending on model availability.
373 stars and 886 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
373
Forks
43
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 08, 2025
Monthly downloads
886
Commits (30d)
0
Dependencies
12
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Softcatala/open-dubbing"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
pnnbao97/VieNeu-TTS
Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 24kHz audio...
r9y9/nnmnkwii
Library to build speech synthesis systems designed for easy and fast prototyping.
CorentinJ/Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
babysor/MockingBird
🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time
Amey-Thakur/DEEPFAKE-AUDIO
🎙️ Deepfake Audio – A neural voice cloning studio powered by SV2TTS technology.