LibreAI / Audio / Real-Time-Voice-Cloning

// audio · CorentinJ/Real-Time-Voice-Cloning

Real-Time-Voice-Cloning

Real-Time-Voice-Cloning es un proyecto de audio de código abierto de CorentinJ (CorentinJ/Real-Time-Voice-Cloning en GitHub). Tiene 60.173 estrellas en GitHub y 9.377 bifurcaciones, se publica bajo la licencia NOASSERTION y se actualizó por última vez en GitHub el 9 de marzo de 2026.

Clone a voice from 5 seconds of audio and generate arbitrary speech in real time

★ 60,2k estrellas⑂ 9,4k bifurcacionesNOASSERTIONactualizado mar 2026

Ver en GitHub ↗

▦ visual: el README de este proyecto no incluye ninguna captura incrustable,
así que aquí va un marcador. La guía de abajo está completa de todos modos.

// datos del proyecto

Datos del proyecto

Repositorio: CorentinJ/Real-Time-Voice-Cloning
Estrellas en GitHub: 60.173
Bifurcaciones: 9.377
Licencia: NOASSERTION
Última actualización en GitHub: 9 de marzo de 2026
Categoría: Audio
Tipo de ficha: Guía de instalación completa

// cómo funciona

Cómo funciona

Clarify your goal
Decide what you want from Real-Time-Voice-Cloning and check the README and requirements to confirm it fits your setup and Python environment.
Get the code
Clone the repository from GitHub (github.com/CorentinJ/Real-Time-Voice-Cloning) or use the documented install channel if you do not need the source.
Install and configure
Follow the README quickstart to install dependencies and set any required configuration or credentials.
Run your first task
Work through the README's first example end to end, then adapt it to your own project or data.

// características

Por qué gusta tanto

5-second cloning

Clones a voice from just a few seconds of reference audio.

Real-time synthesis

Generates arbitrary speech in the cloned voice in real time.

Toolbox GUI

Ships an interactive toolbox demo for trying cloning without code.

CLI demo

Also provides a command-line demo for scripted use.

Research implementation

Implements the published encoder, synthesizer and vocoder papers listed in the README.

Pretrained models

Optional pretrained models are available to download, per the README.

// ejecútalo

Ejecútalo tú mismo

Clone the repository

Start by getting the source and entering the project directory.

git clone https://github.com/CorentinJ/Real-Time-Voice-Cloning.git
cd Real-Time-Voice-Cloning

Install with uv
The README now drives everything through uv; install uv first if needed.
```
pip install -U uv
```
Run the toolbox
Launch the GUI toolbox with the CUDA or CPU extra depending on your hardware.
```
uv run --extra cpu demo_toolbox.py
```

// casos de uso

Qué puedes crear

Prototyping voice cloning for accessibility tools
Researching encoder-vocoder speech pipelines
Generating character voices for indie games
Demonstrating few-shot voice cloning in a class or talk

Readers working through the Audio shelf also stop at koma, self-hosted AI video analysis: summaries, chapters, transcripts. Open-Cluely opens source no-cost alternative to Cluely & Parakeet AI. The Audio shelf also holds clashgram — Web is an open source, glassmorphic client.

// preguntas frecuentes

Preguntas frecuentes

Who maintains Real-Time-Voice-Cloning?

It is maintained by CorentinJ and contributors on GitHub, where the repository github.com/CorentinJ/Real-Time-Voice-Cloning is the canonical home for code, issues and releases.

Is Real-Time-Voice-Cloning free to use?

Yes — it is open source under the NOASSERTION license. Read the license in the repository for what is permitted, including any conditions on redistribution or commercial use.

Does it need a paid API key?

No. Everything runs locally; a GPU is recommended but a CPU path is documented.

How does Real-Time-Voice-Cloning compare to alternatives?

Compared with Coqui TTS: This project focuses specifically on fast voice cloning from seconds of audio, while Coqui TTS is a broader multi-model TTS toolkit.

How do I get started?

Los demás proyectos de Audio con más estrellas del catálogo de LibreAI: la lista realista de alternativas si Real-Time-Voice-Cloning no es lo que buscas.

MoneyPrinterTurbo★ 128,3k
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
Whisper★ 109,9k
Robust Speech Recognition via Large-Scale Weak Supervision
GPT-SoVITS★ 62,3k
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
whisper.cpp★ 54,1k
Port of OpenAI's Whisper model in C/C++
VoiceStudio★ 52,6k
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creatio…

// más en audio

Más en Audio

Proyectos de Audio cercanos en el catálogo, los más próximos en estrellas a Real-Time-Voice-Cloning: sigue explorando a ambos lados.

GPT-SoVITS★ 62,3k
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
whisper.cpp★ 54,1k
Port of OpenAI's Whisper model in C/C++
Whisper★ 109,9k
Robust Speech Recognition via Large-Scale Weak Supervision
VoiceStudio★ 52,6k
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creatio…
MoneyPrinterTurbo★ 128,3k
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
Coqui TTS★ 46,1k
Deep learning toolkit for text-to-speech, battle-tested in research and production

Consigue Real-Time-Voice-Cloning

Gratis y abierto: consigue el código fuente, dale una estrella al repositorio y empieza a crear.

Ver en GitHub ↗← Más herramientas de Audio