About Eleven 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.
| Metric | Value |
|---|---|
| Max Output | 10 minutes |
| Multilingual | Yes (vocals in English, Spanish, German, Japanese, and more) |
Ready to build with Eleven Music v2.5?
Try Eleven Music v2.5 in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "elevenlabs-music-v2-5",
"messages": [
{
"role": "user",
"content": "Try sending a message."
}
]
}'Request parameters
Every field Eleven Music v2.5 accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/chat/completions| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Describe the song: genre, mood, instruments, tempo, vocals, and structure. |
lyrics_text | stringnullable | No | — | Optional lyrics to sing. Leave empty to let the model write lyrics from the prompt. |
duration | integer | No | 30 | Range: 3 – 600 |
force_instrumental | boolean | No | false | Guarantee an instrumental track with no vocals. Cannot be combined with lyrics. |