Try Eleven Music v2.5 in the Workbench
Run this model interactively, tune parameters, and compare outputs.
elevenlabs-music-v2-5
Eleven Music v2.5 generates complete songs from a text prompt, with or without vocals, in any genre and in multiple languages.
Describe the genre, mood, instrumentation, tempo, and structure in natural language, and optionally supply your own lyrics. Tracks run from 3 seconds to 10 minutes, and an instrumental switch guarantees no vocals for background and score use. Compared with Music v2 it improves prompt adherence and gives richer melodies and more layered arrangements, with the largest gains in vocal-led and acoustic genres. Output is 44.1 kHz stereo.
Example request
- Minimal
- All parameters
Fetch model details
The models endpoint returns the full model object, including itsjson_request_schema.