Who it is built for
- Developers reviewing Coqui TTS documentation
- Python users running supported TTS models
- Teams evaluating archived XTTS v2 capabilities
Discontinued speech synthesis and voice generation platform
Coqui announced that its service was shutting down, and its former product domain no longer serves the product. Official TTS documentation remains accessible for its Python library, including XTTS v2 capabilities for multilingual speech synthesis and voice cloning.
The decision
Start with the job, the team, and the constraints. Product fit becomes much clearer when those three line up.
Inside the product
The core product capabilities, grouped around the work they enable.
The documentation describes XTTS v2 as supporting 16 languages and streaming speech generation.
The Python API supports voice cloning with a speaker reference audio file and a selected language.
The remaining documentation provides installation, model, training, server, command-line, and Python API guidance.
Install the TTS Python package and select a supported model. Provide text and, for multilingual voice cloning, a reference audio file and language to generate an audio output.
Plans and official links
See the entry price, free access options, company details, and direct vendor destinations in one place.
Choosing for a real workflow?
We map the workflow, connect existing systems, choose what to buy, and build what is missing.