IndexTTS

by bilibili Index Team

bilibili's dubbing-oriented TTS: voice cloning with controllable emotion and speed.

24.4 k stars GitHub bilibili Model Use License Free when localOpen weightsLocal

View on GitHub →

What it does

Voice cloning with emotion set independently from timbre
Adjustable speaking speed (0.5x to 2x duration)
IndexTTS-2.5: Chinese, English, Japanese, Spanish and Arabic, web UI included

Install it

Requirements: Git and uv.

Clone the repository

git clone https://github.com/index-tts/index-tts.git && cd index-tts

Install dependencies

uv sync --all-extras

Download the models

uv tool install "huggingface-hub" && hf download IndexTeam/IndexTTS-2.5 --local-dir=checkpoints

Launch the web UI

uv run webui.py

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 IndexTTS (https://github.com/index-tts/index-tts) on my machine.
1. Check the requirements: Git and uv. If anything is missing, tell me before installing anything.
2. Follow the official method:
- Clone the repository: git clone https://github.com/index-tts/index-tts.git && cd index-tts
- Install dependencies: uv sync --all-extras
- Download the models: uv tool install "huggingface-hub" && hf download IndexTeam/IndexTTS-2.5 --local-dir=checkpoints
- Launch the web UI: uv run webui.py
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.