Eleven Labs API

The Eleven Labs API delivers high-fidelity, ultra-low-latency AI voice generation: convert text-to-speech, clone voices, and support 70+ languages.

This is the premier AI voice synthesis platform for developers: integrate lifelike, emotionally rich audio into your applications. The API supports core Text-to-Speech (TTS) and Speech-to-Speech (STS) functionality, utilizing models like `Eleven v3` for expressive speech across over 70 languages. Expect performance: the `Eleven Flash v2.5` model offers ultra-low latency, generating audio in approximately 75ms. Access is via a robust REST API, with official SDKs available for Python and Node.js, making high-quality voice cloning and real-time audio generation straightforward.

https://elevenlabs.io/docs