XTTS-v2 API

XTTS-v2 is an expressive, open-source voice cloning and text-to-speech model developed by Coqui AI, designed to generate highly natural and emotionally rich speech from minimal input. With the ability to clone a speaker’s voice using only a few seconds of reference audio, it enables realistic voice reproduction across multiple languages while preserving tone, style, and personality. The model supports cross-language speech synthesis, allowing a voice captured in one language to speak fluently in another. Optimized for near real-time performance and flexible deployment, XTTS-v2 is well suited for voice assistants, interactive applications, content creation, and privacy-focused self-hosted TTS systems.