
Real-Time Voice Cloning
Free open source AI voice cloning and text to speech synthesis. Clone a voice in 5 seconds to generate arbitrary speech in real-time
- Free • Open Source
- Windows
- Linux
- Python
What is Real-Time Voice Cloning?
SV2TTS is a three-stage deep learning framework that allows to create a numerical representation of a voice from a few seconds of audio, and to use it to condition a text-to-speech model trained to generalize to new voices.
Real-Time Voice Cloning Screenshots



No features, maybe you want to suggest one?
Suggest and vote on featuresReal-Time Voice Cloning information
Supported Languages
- English
GitHub repository
- 41,875 Stars
- 7,610 Forks
- 136 Open Issues
- Updated
Comments and Reviews
Tags
- deepfake
- voices
- cloning
Recent user activities on Real-Time Voice Cloning
Maoholguin added Real-Time Voice Cloning as alternative(s) to Wondercraft AI
Maoholguin added Real-Time Voice Cloning as alternative(s) to iMyFone VoxBox
Maoholguin added Real-Time Voice Cloning as alternative(s) to HeyGen
Not easy to compile apparently, one user under the video comments suggested "DID IT !!!!!! Had errors so hours of troubleshooting. Use anaconda with a virtual environment theres a command for getting cuda, and others all working from the virtual env. !", there is also a video tutorial here https://www.youtube.com/watch?v=pKoOw5a74XU
and here https://www.youtube.com/watch?v=12rdn9jazwE