Try Eleven v4 in the Workbench
Run this model interactively, tune parameters, and compare outputs.
elevenlabs-eleven-v4
Eleven v4 is a text-to-speech model built for expressive, emotionally rich speech across more than 90 languages.
Inline audio tags such as [whispering], [laughing], or [quietly curious] direct the delivery line by line, and punctuation and ellipses shape pacing. It suits character voiceover for games and animation, audiobooks and long-form narration, and multilingual content that has to keep one voice consistent across languages. A single request takes up to 10,000 characters, roughly ten minutes of audio. Two voice settings, Stability and Similarity, control how varied the delivery is and how closely it follows the voice.
Example request
- Minimal
- All parameters
Fetch model details
The models endpoint returns the full model object, including itsjson_request_schema.