# OpenRouter APIs — ElevenLabs: Eleven Multilingual v2 (elevenlabs/eleven-multilingual-v2)

Guide for calling every confirmed OpenRouter API that serves `elevenlabs/eleven-multilingual-v2`.

Model page: https://openrouter.ai/elevenlabs/eleven-multilingual-v2
Create an API key: https://openrouter.ai/settings/keys

## Pricing

Standard-variant prices for `elevenlabs/eleven-multilingual-v2`, per provider, in the unit each provider bills (tokens, images, seconds of video, or characters of audio). Pay-as-you-go with no markup on the provider's price.

- ElevenLabs: $80/M characters

Full price table, including other variants and per-request charges: https://openrouter.ai/elevenlabs/eleven-multilingual-v2
How OpenRouter prices requests: https://openrouter.ai/pricing

## EU in-region routing

`elevenlabs/eleven-multilingual-v2` is not currently available through EU in-region routing.

Docs: https://openrouter.ai/docs/guides/features/in-region-routing

## Authentication

Send this header with every request:

- Authorization: Bearer $OPENROUTER_API_KEY

## Text-to-Speech API

Synthesize audio with `elevenlabs/eleven-multilingual-v2` through OpenRouter's Text-to-Speech API.

Docs: https://openrouter.ai/docs/api/api-reference/tts/create-speech

### Endpoint

POST https://openrouter.ai/api/v1/audio/speech

Headers:
- Content-Type: application/json

### Request fields (elevenlabs/eleven-multilingual-v2)

- model: string (required) — `"elevenlabs/eleven-multilingual-v2"`
- input: string (required) — text to synthesize
- voice: "george" | "sarah" | "adam" | "alice" | "bella" | "bill" | "brian" | "callum" | "charlie" | "chris" | "daniel" | "eric" | "harry" | "jessica" | "laura" | "liam" | "lily" | "matilda" | "river" | "roger" | "will" (optional) — provider-specific voice identifier
- response_format: "mp3" | "pcm" (optional) — output audio encoding; defaults to pcm

### Response

Success returns raw audio bytes, not JSON.

- `Content-Type` identifies the audio encoding, such as `audio/mpeg` or `audio/pcm`.
- `X-Generation-Id` identifies the billed generation.
- Write the response body directly to an audio file; do not call `response.json()`.

### Examples

#### Text to Speech

```bash
curl https://openrouter.ai/api/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  --output output.mp3 \
  -d '{
  "model": "elevenlabs/eleven-multilingual-v2",
  "input": "Every request finds its way. Pick a model, keep your code, and let the router handle the rest. One interface, hundreds of models, ready when you are.",
  "voice": "george",
  "response_format": "mp3",
  "speed": 1
}'
```

#### Text to Speech 2

```bash
curl https://openrouter.ai/api/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  --output output.mp3 \
  -d '{
  "model": "elevenlabs/eleven-multilingual-v2",
  "input": "The rain had not stopped for three days. Mara pulled her coat tighter and stepped onto the platform, where the last train of the night waited with its doors open and its windows fogged. She did not know where it was going. That, she decided, was the point. Somewhere behind her, the city kept its own time, and for once she let it.",
  "voice": "daniel",
  "response_format": "mp3",
  "speed": 1
}'
```

#### Text to Speech 3

```bash
curl https://openrouter.ai/api/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  --output output.mp3 \
  -d '{
  "model": "elevenlabs/eleven-multilingual-v2",
  "input": "La luz cálida recorre la ciudad mientras cae la tarde. Una sola interfaz, cientos de modelos. Listos cuando tú lo estés.",
  "voice": "matilda",
  "response_format": "mp3",
  "speed": 1
}'
```

#### Text to Speech 4

```bash
curl https://openrouter.ai/api/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  --output output.mp3 \
  -d '{
  "model": "elevenlabs/eleven-multilingual-v2",
  "input": "Every request finds its way. Pick a model, keep your code, and let the router handle the rest. One interface, hundreds of models, ready when you are.",
  "voice": "george",
  "response_format": "mp3",
  "speed": 1,
  "provider": {
    "options": {
      "elevenlabs": {
        "voice_settings": {
          "stability": 0.1
        }
      }
    }
  }
}'
```

#### Text to Speech 5

```bash
curl https://openrouter.ai/api/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  --output output.mp3 \
  -d '{
  "model": "elevenlabs/eleven-multilingual-v2",
  "input": "Every request finds its way. Pick a model, keep your code, and let the router handle the rest. One interface, hundreds of models, ready when you are.",
  "voice": "george",
  "response_format": "mp3",
  "speed": 1,
  "provider": {
    "options": {
      "elevenlabs": {
        "voice_settings": {
          "stability": 0.95
        }
      }
    }
  }
}'
```

#### Text to Speech 6

```bash
curl https://openrouter.ai/api/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  --output output.mp3 \
  -d '{
  "model": "elevenlabs/eleven-multilingual-v2",
  "input": "Every request finds its way. Pick a model, keep your code, and let the router handle the rest. One interface, hundreds of models, ready when you are.",
  "voice": "george",
  "response_format": "mp3",
  "speed": 1,
  "provider": {
    "options": {
      "elevenlabs": {
        "voice_settings": {
          "style": 0.8
        }
      }
    }
  }
}'
```

#### Text to Speech 7

```bash
curl https://openrouter.ai/api/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  --output output.mp3 \
  -d '{
  "model": "elevenlabs/eleven-multilingual-v2",
  "input": "Every request finds its way. Pick a model, keep your code, and let the router handle the rest. One interface, hundreds of models, ready when you are.",
  "voice": "george",
  "response_format": "mp3",
  "speed": 1,
  "provider": {
    "options": {
      "elevenlabs": {
        "voice_settings": {
          "use_speaker_boost": false
        }
      }
    }
  }
}'
```

#### Text to Speech 8

```bash
curl https://openrouter.ai/api/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  --output output.mp3 \
  -d '{
  "model": "elevenlabs/eleven-multilingual-v2",
  "input": "すべてのリクエストは道を見つけます。モデルを選び、コードはそのまま、あとはルーターにお任せください。ひとつのインターフェースで、数百のモデルがいつでも使えます。",
  "voice": "george",
  "response_format": "mp3",
  "speed": 1,
  "provider": {
    "options": {
      "elevenlabs": {
        "language_code": "ja"
      }
    }
  }
}'
```

#### Text to Speech 9

```bash
curl https://openrouter.ai/api/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  --output output.mp3 \
  -d '{
  "model": "elevenlabs/eleven-multilingual-v2",
  "input": "Cada solicitud encuentra su camino. Elige un modelo, conserva tu código y deja que el router haga el resto. Una interfaz, cientos de modelos, listos cuando tú.",
  "voice": "george",
  "response_format": "mp3",
  "speed": 1,
  "provider": {
    "options": {
      "elevenlabs": {
        "language_code": "es"
      }
    }
  }
}'
```

### Error differences

- 400 — malformed audio input or an audio option the routed provider does not support
- 502 — the upstream audio operation failed

## Errors

Failures return `{"error": {"code": <number>, "message": <string>}}` with the HTTP status:

- 400 — malformed request or an unsupported parameter
- 401 — missing or invalid API key
- 402 — insufficient credits
- 403 — spend limit reached, key disabled, or access blocked
- 404 — unknown model or no provider can serve the request
- 429 — rate limited; retry with backoff
- 502 — the operation failed upstream; failed generations are not billed

---

Canonical version of this document: https://openrouter.ai/elevenlabs/eleven-multilingual-v2/llms.txt
