Coqui TTS (XTTS)

by Idiap Research Institute (fork de Coqui)

Coqui's TTS toolkit, maintained by Idiap, with XTTS-v2 to clone a voice in seconds.

2,337 stars GitHub MPL-2.0 FreeOpen sourceOpen weightsLocal

View on GitHub →

What it does

XTTS-v2: multilingual voice cloning (17 languages) from a short sample
Hundreds of ready models, up to ~1,100 languages via Fairseq models
Tools to train or fine-tune your own models; note XTTS weights have their own non-commercial license

Install it

Requirements: Python and uv (or pip), PyTorch.

Install PyTorch

uv pip install torch torchaudio torchcodec --torch-backend=auto

Install Coqui TTS

uv pip install coqui-tts

Try it

tts --text "Text for TTS" --out_path output/path/speech.wav

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 Coqui TTS (XTTS) (https://github.com/idiap/coqui-ai-TTS) on my machine.
1. Check the requirements: Python and uv (or pip), PyTorch. If anything is missing, tell me before installing anything.
2. Follow the official method:
- Install PyTorch: uv pip install torch torchaudio torchcodec --torch-backend=auto
- Install Coqui TTS: uv pip install coqui-tts
- Try it: tts --text "Text for TTS" --out_path output/path/speech.wav
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.