F5-TTS

by SWivid (SJTU X-LANCE)

Voice cloning from a few seconds of audio, with a ready-to-use web UI.

15.4 k stars GitHub MIT FreeOpen sourceOpen weightsLocal

View on GitHub →

What it does

Reproduce a voice from a short reference clip and its transcript
Gradio UI: multi-voice, dialogues and model fine-tuning
MIT code, but pretrained weights are CC-BY-NC (non-commercial)

Install it

Requirements: Python 3.11 (Conda recommended) and PyTorch for your GPU.

Create the environment

conda create -n f5-tts python=3.11 && conda activate f5-tts

Install with pip

pip install f5-tts

Launch the web UI

f5-tts_infer-gradio

The prompt for your agent

Paste it into your coding agent: it checks the requirements and installs it for you.

Claude CodeCodexCursorGemini CLIopencode

Prompt

Install F5-TTS (https://github.com/SWivid/F5-TTS) on my machine.
1. Check the requirements: Python 3.11 (Conda recommended) and PyTorch for your GPU. If anything is missing, tell me before installing anything.
2. Follow the official method:
- Create the environment: conda create -n f5-tts python=3.11 && conda activate f5-tts
- Install with pip: pip install f5-tts
- Launch the web UI: f5-tts_infer-gradio
3. Check that it works, then explain how to launch it and where to start.

Always review what your agent is about to run, especially install commands.