Atm4x/tts-with-rvc

TTS with RVC-module to generate .wav audios

54
/ 100
Established

Combines Edge TTS with Retrieval-based Voice Conversion (RVC) to apply custom voice models to synthesized speech, supporting multiple F0 extraction methods (RMVPE, FCPE, PM, Harvest, DIO, Crepe) and index-based voice blending. The pipeline generates audio via Edge TTS, then processes it through RVC with configurable pitch transposition, voice envelope scaling, and consonant protection. Built on PyTorch with CUDA/MPS acceleration and integrates ffmpeg for audio processing.

No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 2 / 25
Adoption 13 / 25
Maturity 25 / 25
Community 14 / 25

How are scores calculated?

Stars

40

Forks

6

Language

Python

License

MIT

Last pushed

Sep 17, 2025

Monthly downloads

366

Commits (30d)

0

Dependencies

23

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Atm4x/tts-with-rvc"

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