#2 · Primary category： Speech & Audio
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
Project last updated：03/09/26
GitHub Stars
60.1K
Forks
9.4K
Contributors
20
License
Other
Why we included this project
This is one of the most widely studied open-source implementations of voice cloning, built around the SV2TTS framework. It captures a voice from a few seconds of reference audio, then uses that embedding to drive a text-to-speech synthesizer and a real-time vocoder. The bundled toolbox gives you a GUI for recording a sample and typing text, and you hear the cloned voice right away, with a command-line path for scripting. The author is upfront that the codebase has aged and commercial services now deliver cleaner audio, so it works best as a reference implementation and a way to learn how speaker verification and multispeaker synthesis fit together, not as a production TTS engine.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
whisper.cpp
Port of OpenAI's Whisper model in C/C++
VibeVoice
Open-Source Frontier Voice AI
voicebox
The open-source AI voice studio. Clone, dictate, create.
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
ChatTTS
A generative speech model for daily dialogue.