Coqui TTS is a Python library for turning text into speech, with pretrained voices in many languages and tools to train or fine-tune your own.
In plain words
Text-to-speech models read text aloud. Coqui TTS bundles many such models behind one library, including XTTS, which can copy a voice from a reference audio clip and stream audio quickly. It also includes tools for training new models, fine-tuning existing ones and preparing datasets. The original repository is no longer maintained; a community fork keeps releasing it under the package name coqui-tts.
A quick example
Imagine you want an app to read news articles aloud in Spanish. You install the library, pick a pretrained multilingual model, and pass it each article's text and a language code. The model returns an audio file you can play in the app.
Where you'll meet it
- Reading text aloud in many languages.
- Voice cloning and voice conversion experiments.
- Training custom voices in new languages.
Related
Sources
- Docsidiap/coqui-ai-TTS, Idiap (GitHub) · read 29 Sept 2026
- Docscoqui-ai/TTS, Coqui (GitHub) · read 29 Sept 2026
Checked by WhatIsAI against the sources above · 29 Sept 2026. Spotted an error? Report it.