ElevenLabs

ElevenLabs provides high-quality AI voice technology, including speech-to-text capabilities through their transcription API.

Quick Start

LiteLLM Python SDK

# Transcribe audio file
with open("audio.mp3", "rb") as audio_file:
    response = litellm.transcription(
        model="elevenlabs/scribe_v1",
        file=audio_file,
        api_key="your-elevenlabs-api-key"  # or set ELEVENLABS_API_KEY env var
    )

print(response.text)

# Transcribe with speaker diarization and language specification
with open("audio.wav", "rb") as audio_file:
    response = litellm.transcription(
        model="elevenlabs/scribe_v1",
        file=audio_file,
        language="en",           # Language hint (maps to language_code)
        temperature=0.3,         # Control randomness in transcription
        diarize=True,           # Enable speaker diarization
        api_key="your-elevenlabs-api-key"
    )

print(f"Transcription: {response.text}")
print(f"Language: {response.language}")

# Access word-level timestamps if available
if hasattr(response, 'words') and response.words:
    for word_info in response.words:
        print(f"Word: {word_info['word']}, Start: {word_info['start']}, End: {word_info['end']}")

async def transcribe_audio():
    with open("audio.mp3", "rb") as audio_file:
        response = await litellm.atranscription(
            model="elevenlabs/scribe_v1",
            file=audio_file,
            api_key="your-elevenlabs-api-key"
        )
    
    return response.text

# Run async transcription
result = asyncio.run(transcribe_audio())
print(result)

LiteLLM Proxy

1. Configure your proxy

model_list:
  - model_name: elevenlabs-transcription
    litellm_params:
      model: elevenlabs/scribe_v1
      api_key: os.environ/ELEVENLABS_API_KEY

general_settings:
  master_key: your-master-key

2. Start the proxy

litellm --config config.yaml

# Proxy will be available at http://localhost:4000

3. Make transcription requests

curl http://localhost:4000/v1/audio/transcriptions \\
  -H "Authorization: Bearer $LITELLM_API_KEY" \\
  -H "Content-Type: multipart/form-data" \\
  -F file="@audio.mp3" \\
  -F model="elevenlabs-transcription" \\
  -F language="en" \\
  -F temperature="0.3"

from openai import OpenAI

# Initialize client with your LiteLLM proxy URL
client = OpenAI(
    base_url="http://localhost:4000",
    api_key="your-litellm-api-key"
)

# Transcribe audio file
with open("audio.mp3", "rb") as audio_file:
    response = client.audio.transcriptions.create(
        model="elevenlabs-transcription",
        file=audio_file,
        language="en",
        temperature=0.3,
        # ElevenLabs-specific parameters
        diarize=True,
        speaker_boost=True,
        custom_vocabulary="technical,AI,machine learning"
    )

print(response.text)

const openai = new OpenAI({
  baseURL: 'http://localhost:4000',
  apiKey: 'your-litellm-api-key'
});

async function transcribeAudio() {
  const response = await openai.audio.transcriptions.create({
    file: fs.createReadStream('audio.mp3'),
    model: 'elevenlabs-transcription',
    language: 'en',
    temperature: 0.3,
    diarize: true,
    speaker_boost: true
  });

  console.log(response.text);
}

transcribeAudio();

Response Format

ElevenLabs returns transcription responses in OpenAI-compatible format:

{
  "text": "Hello, this is a sample transcription with multiple speakers.",
  "task": "transcribe",
  "language": "en",
  "words": [
    {
      "word": "Hello",
      "start": 0.0,
      "end": 0.5
    },
    {
      "word": "this",
      "start": 0.5,
      "end": 0.8
    }
  ]
}

Common Issues

1. Invalid API Key: Ensure ELEVENLABS_API_KEY is set correctly

---

Text-to-Speech (TTS)

ElevenLabs provides high-quality text-to-speech capabilities through their TTS API, supporting multiple voices, languages, and audio formats.

Overview

Supported Models

Quick Start

LiteLLM Python SDK

os.environ["ELEVENLABS_API_KEY"] = "your-elevenlabs-api-key"

# Basic usage with voice mapping
audio = litellm.speech(
    model="elevenlabs/eleven_multilingual_v2",
    input="Testing ElevenLabs speech from LiteLLM.",
    voice="alloy",  # Maps to ElevenLabs voice ID automatically
)

# Save audio to file
with open("test_output.mp3", "wb") as f:
    f.write(audio.read())

Using Eleven v3 with Audio Tags

Eleven v3 supports audio tags for adding sound effects and pauses directly in the text:

os.environ["ELEVENLABS_API_KEY"] = "your-elevenlabs-api-key"

audio = litellm.speech(
    model="elevenlabs/eleven_v3",
    input='Welcome back. <sfx>applause</sfx> Today we have a special guest. <pause duration="1.5s"/> Let me introduce them.',
    voice="alloy",
)

with open("eleven_v3_output.mp3", "wb") as f:
    f.write(audio.read())

Advanced Usage: Overriding Parameters and ElevenLabs-Specific Features

os.environ["ELEVENLABS_API_KEY"] = "your-elevenlabs-api-key"

# Example showing parameter overriding and ElevenLabs-specific parameters
audio = litellm.speech(
    model="elevenlabs/eleven_multilingual_v2",
    input="Testing ElevenLabs speech from LiteLLM.",
    voice="alloy",  # Can use mapped voice name or raw ElevenLabs voice_id
    response_format="pcm",  # Maps to ElevenLabs output_format
    speed=1.1,  # Maps to voice_settings.speed
    # ElevenLabs-specific parameters - passed directly to API
    pronunciation_dictionary_locators=[
        {"pronunciation_dictionary_id": "dict_123", "version_id": "v1"}
    ],
    model_id="eleven_multilingual_v2",  # Override model if needed
)

# Save audio to file
with open("test_output.mp3", "wb") as f:
    f.write(audio.read())

Voice Mapping

LiteLLM automatically maps common OpenAI voice names to ElevenLabs voice IDs:

Using Custom Voice IDs: You can also pass any ElevenLabs voice ID directly. If the voice name is not in the mapping, LiteLLM will use it as-is:

audio = litellm.speech(
    model="elevenlabs/eleven_multilingual_v2",
    input="Testing with a custom voice.",
    voice="21m00Tcm4TlvDq8ikWAM",  # Direct ElevenLabs voice ID
)

Response Format Mapping

LiteLLM maps OpenAI response formats to ElevenLabs output formats:

You can also pass ElevenLabs-specific output formats directly using the output_format parameter.

Supported Parameters

audio = litellm.speech(
    model="elevenlabs/eleven_multilingual_v2",  # Required
    input="Text to convert to speech",           # Required
    voice="alloy",                               # Required: Voice selection (mapped or raw ID)
    response_format="mp3",                      # Optional: Audio format (mp3, pcm, opus)
    speed=1.0,                                  # Optional: Speech speed (maps to voice_settings.speed)
    # ElevenLabs-specific parameters (passed directly):
    model_id="eleven_multilingual_v2",           # Optional: Override model
    voice_settings={                             # Optional: Voice customization
        "stability": 0.5,
        "similarity_boost": 0.75,
        "speed": 1.0
    },
    pronunciation_dictionary_locators=[         # Optional: Custom pronunciation
           {"pronunciation_dictionary_id": "dict_123", "version_id": "v1"}
    ],
)

LiteLLM Proxy

1. Configure your proxy

model_list:
  - model_name: elevenlabs-tts
    litellm_params:
      model: elevenlabs/eleven_multilingual_v2
      api_key: os.environ/ELEVENLABS_API_KEY

general_settings:
  master_key: your-master-key

2. Make TTS requests

Simple Usage (OpenAI Parameters)

You can use standard OpenAI-compatible parameters without any provider-specific configuration:

curl http://localhost:4000/v1/audio/speech \\
  -H "Authorization: Bearer $LITELLM_API_KEY" \\
  -H "Content-Type: application/json" \\
  -d '{
    "model": "elevenlabs-tts",
    "input": "Testing ElevenLabs speech via the LiteLLM proxy.",
    "voice": "alloy",
    "response_format": "mp3"
  }' \\
  --output speech.mp3

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:4000",
    api_key="your-litellm-api-key"
)

response = client.audio.speech.create(
    model="elevenlabs-tts",
    input="Testing ElevenLabs speech via the LiteLLM proxy.",
    voice="alloy",
    response_format="mp3"
)

# Save audio
with open("speech.mp3", "wb") as f:
    f.write(response.content)

Advanced Usage (ElevenLabs-Specific Parameters)

Note: When using the proxy, provider-specific parameters (like pronunciation_dictionary_locators, voice_settings, etc.) must be passed in the extra_body field.

curl http://localhost:4000/v1/audio/speech \\
  -H "Authorization: Bearer $LITELLM_API_KEY" \\
  -H "Content-Type: application/json" \\
  -d '{
    "model": "elevenlabs-tts",
    "input": "Testing ElevenLabs speech via the LiteLLM proxy.",
    "voice": "alloy",
    "response_format": "pcm",
    "extra_body": {
      "pronunciation_dictionary_locators": [
          {"pronunciation_dictionary_id": "dict_123", "version_id": "v1"}
      ],
      "voice_settings": {
        "speed": 1.1,
        "stability": 0.5,
        "similarity_boost": 0.75
      }
    }
  }' \\
  --output speech.mp3

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:4000",
    api_key="your-litellm-api-key"
)

response = client.audio.speech.create(
    model="elevenlabs-tts",
    input="Testing ElevenLabs speech via the LiteLLM proxy.",
    voice="alloy",
    response_format="pcm",
    extra_body={
        "pronunciation_dictionary_locators": [
               {"pronunciation_dictionary_id": "dict_123", "version_id": "v1"}
        ],
        "voice_settings": {
            "speed": 1.1,
            "stability": 0.5,
            "similarity_boost": 0.75
        }
    }
)

# Save audio
with open("speech.mp3", "wb") as f:
    f.write(response.content)