# ElevenLabs v3

> ElevenLabs' most expressive text-to-speech model. 26 premium voices, audio tags like [laughs] and [whispers], style/stability controls, and 70+ language support.

- **Provider**: replicate
- **Model ID**: elevenlabs/v3
- **Category**: tts_voice
- **Credits**: 237 per request
- **Pricing Type**: token_based

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `speed` (number, optional): Speed of speech (0.25 to 4.0) (Default: `1`; Range: min: 0.7, max: 1.2)
- `style` (number, optional): Style exaggeration (0.0 to 1.0) (Default: `0`; Range: min: 0, max: 1)
- `prompt` (string, **required**): The text to convert to speech
- `next_text` (string, optional): Next text for context (Default: ``)
- `stability` (number, optional): Stability setting for voice generation (0.0 to 1.0) (Default: `0.5`; Range: min: 0, max: 1)
- `language_code` (string, optional): Language code (e.g., 'en', 'es', 'fr') (Default: `en`; Options: `en`, `ko`, `ja`, `zh`, `de`, `hi`, `fr`, `pt`, `it`, `es`, `id`, `nl`, `tr`, `fil`, `pl`, `sv`, `bg`, `ro`, `ar`, `cs`, `el`, `fi`, `hr`, `ms`, `sk`, `da`, `ta`, `uk`, `ru`, `hu`, `no`, `vi`)
- `voice` (string, optional): Voice choice for speech generation (Default: `Rachel`; Options: `Rachel`, `Drew`, `Clyde`, `Paul`, `Aria`, `Domi`, `Dave`, `Roger`, `Fin`, `Sarah`, `James`, `Jane`, `Juniper`, `Arabella`, `Hope`, `Bradford`, `Reginald`, `Gaming`, `Austin`, `Kuon`, `Blondie`, `Priyanka`, `Alexandra`, `Monika`, `Mark`, `Grimblewood`)
- `similarity_boost` (number, optional): Similarity boost setting (0.0 to 1.0) (Default: `0.75`; Range: min: 0, max: 1)
- `previous_text` (string, optional): Previous text for context (Default: ``)

## Example Request

```json
{
  "model": "elevenlabs/v3",
  "input": {
    "voice": "Grimblewood",
    "language_code": "en",
    "next_text": "",
    "similarity_boost": 0.75,
    "style": 0,
    "previous_text": "",
    "prompt": "In the ancient land of Eldoria, where skies shimmered and forests, whispered secrets to the wind, lived a dragon named Zephyros. Not the \u201cburn it all down\u201d kind, but he was gentle, wise, with eyes like old stars. Even the birds fell silent when he passed.",
    "speed": 1,
    "stability": 0.5
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

text-to-speech, tts, audio, voice-synthesis, elevenlabs, expressive, multilingual

## Documentation

https://replicate.com/elevenlabs/v3


## Token Pricing

- Input: 0.2325 credits/token
- Output: 0.2325 credits/token