ElevenLabs v4 - Argil

Model id elevenlabs-4 · ElevenLabs · audio · 1 mode: text-to-speech.

This page reflects the current catalog. Inputs, allowed values, limits and prices can change as the model evolves; the field names and their meaning do not. For the exact schema at any time, your agent calls get_model with the mode.

Text To Speech

Mode text-to-speech. ElevenLabs v4 text to speech, the most expressive ElevenLabs model. Supports audio tags like [laughs] or [whispers].

Input

Field	Type	Required	Allowed	Default	Description
`text`	string	Yes	up to 10,000 characters		The text to speak.
`voice`	object	Yes			The voice to speak with: its id, and its model and settings when they differ from the voice’s own.
`voice.id`	string	Yes			The `id` of one of your voices, or of Argil’s public voices, as `GET /v1/voices` lists them.
`voice.settings`	object				Speech settings; each defaults to the voice’s own.
`voice.settings.speed`	number		0.7 to 1.2		Speech speed (0.7-1.2); default the voice’s own.
`voice.settings.stability`	number		0 to 1		Voice stability (0.0-1.0).
`voice.settings.similarity`	number		0 to 1		Voice similarity (0.0-1.0).
`voice.settings.style`	number		0 to 1		Style exaggeration (0.0-1.0).

Pricing

3.87 credits per 1k characters. Fixed price: charged as estimated. For the exact price of a request, use estimate_generation.

Example

The arguments of generate_media:

{
  "model": "elevenlabs-4",
  "mode": "text-to-speech",
  "input": {
    "text": "Welcome back! Here is what changed this week, in one minute.",
    "voice": {
      "id": "6f1c2a9e-4b7d-4c1e-9a3f-0b5d8e2c7a14"
    }
  }
}