Skip to content
English
Esc
↑↓navigate↵open⌘Jpreview
On this page

ElevenLabs Eleven v4

ElevenLabs' newest text-to-speech model, more expressive than v3, with 90+ languages and audio tags such as [whispers]

Model ID Aliases Endpoint
elevenlabs/eleven-v4 eleven-v4, eleven_v4 Audio generation

Input modes

Mode References Reference roles
text Text only — —

Prompt limit: 5,000 characters; longer prompts are rejected with 400.

Parameters

Parameter Description Values Default Required
voice Voice: Preset voice ID of this model (for example a MiniMax system voice or an ElevenLabs voice ID). The price does not depend on the voice. string JBFqnCBsd6RMkjVDRZzb No
n Outputs per request: Number of outputs from one API request (one Job), not the application batch size. For multiple Jobs, submit separate requests; n=1 does not prevent application-managed batching. 1 1 No

Examples

text input:

{
  "model": "elevenlabs/eleven-v4",
  "input": {
    "type": "text",
    "prompt": "Good morning. The city is still waking up."
  },
  "parameters": {
    "voice": "JBFqnCBsd6RMkjVDRZzb",
    "n": 1
  }
}

The authoritative contract is GET /v1/models/elevenlabs/eleven-v4?view=contract. A valid parameter does not mean every channel can run it, so quote the complete request. Prices and channels are listed in Model Market.