Say it how you want and hear it delivered in a completely different voice, with full control over the performance. Capture whispers, laughs, accents, and subtle emotional cues.
We are excited to announce that our Speech-to-Speech API is now available to the public. For detailed instructions on how to utilize this tool, please visit our comprehensive guide at and our video.
Explore articles by the ElevenLabs team
.webp&w=3840&q=95)
Add a Santa Voice Agent to Your React App in Minutes
Build a real-time Santa Claus AI voice agent in your React app using ElevenLabs. Follow this quick step-by-step guide to create a festive, fully interactive holiday voice experience with WebRTC and the ElevenLabs Agents Platform.

Introducing ElevenLabs UI: Open-source audio & agent components for the web
ElevenLabs UI is a component library to help you build multimodal agents faster.

Eleven v3 (alpha), now available in the API
Eleven v3 (alpha), the most expressive text to speech model, is now available in the API for every developer.

Eleven Music, now available in the API
Eleven Music is the first API for developers trained on licensed data and cleared for broad commercial use.
