In the middle of 2025, Elevenlabs launched Eleven v3 (alpha), its newest speech synthesis model. As it is currently in the alpha stage, the model is not intended for real-time applications in conversational AI. Developers are recommended to produce several outputs for users to choose from during integration.
Eleven v3 is tailored for situations that require natural and emotionally expressive speech, including character interactions, audiobook narration, and emotional conversations. It features a new Text to Dialogue API and offers support for multiple languages via both Text to Dialogue and Text to Speech APIs.
If you'd like to access this model, you can explore the following possibilities:
Use our video cost calculator to compare prices between platforms offering Eleven v3 (alpha) model.
For locally hosted models, see description and additional links at the bottom for versions, repos and tutorials.
