ArkanDash/Multi-Model-RVC-Inference

RVC Inference with multiple model and huggingface support

51
/ 100
Established

This tool helps you modify audio recordings or live microphone input to sound like a different voice. You provide an audio file or speak into a microphone, select a voice model, and the output is your speech transformed into the chosen voice. It's designed for content creators, vocal artists, or anyone looking to experiment with voice modification for creative projects or impersonations.

112 stars.

Use this if you want to convert speech from one voice to another using multiple voice models, including those from HuggingFace, directly from audio files, YouTube links, or live microphone input.

Not ideal if you require advanced, real-time voice modulation for professional live performances with minimal latency or complex audio effects beyond voice conversion.

voice-conversion audio-editing content-creation vocal-synthesis sound-design
No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

112

Forks

29

Language

Python

License

MIT

Last pushed

Oct 25, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ArkanDash/Multi-Model-RVC-Inference"

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