AI · GitHub repo
Retrieval-based-Voice-Conversion-WebUI
Open-source voice conversion and cloning tool with training and real-time GUI
Retrieval-based Voice Conversion (RVC) is an open-source framework designed to train custom voice models and convert vocal audio into targeted speaker voices. It can train effective models with under 10 minutes of clean speech audio, preserving pitch, inflection, and tone. It includes both web interfaces for batch processing and real-time GUIs or VST plugins for live voice alteration.
What it's for
- Clone a creator or speaker voice using a small set of recorded audio clips
- Convert synthesized text-to-speech audio into a realistic natural voice clone
- Perform real-time voice conversion for streaming, gaming, or live communication
- Generate vocal tracks or AI song covers matching specific vocal timbres
Features
- WebUI for model training, dataset preprocessing, and batch audio inference
- Real-time voice changing GUI with low-latency monitoring
- Effective model training using as little as 10 minutes of clean audio
- Integrated audio separation tools to isolate vocals from background noise
- Pitch extraction algorithms and fine-tuning controls to maintain vocal expression
- VST plugin support for integration into digital audio workstations (DAWs)
- CLI and multi-speaker training options
Pricing
Open source. Free and open source (MIT license)
Details
- Type
- GitHub repo
- Category
- AI
- Topic
- Voice Cloning
- Open source
- Yes
- Platforms
- Windows, Linux, Self-hosted, Command line
- For
- Content creators, game streamers, audio engineers, and AI developers
- Alternative to
- ElevenLabs, Resemble AI
- Tags
- rvc, voice cloning, voice changer, audio processing, speech synthesis, open source
Why it was saved
- @overpowered.ai: Achieves highly realistic speech inflection, pitch, and voice cloning to match a creator's natural voice.
Compare
Related
Open-source deep learning toolkit for text-to-speech synthesis and voice cloning.
Open-source emotive text-to-speech foundation model with low conversational latency.
AI voice generator, voice cloning, and conversational agent platform
Ultra-low-latency streaming text-to-speech and instant voice cloning model.
Open-source 1.6B text-to-speech model generating multi-speaker dialogue in one pass.
Open-source zero-shot text-to-speech and voice cloning model
Updated