ElevenLabs

​

Overview

ElevenLabsTTSService provides high-quality text-to-speech synthesis using ElevenLabs’ WebSocket API. It supports real-time streaming, word-level timing, and various voice customization options.

​

Installation

To use ElevenLabsTTSService, install the required dependencies:

pip install pipecat-ai[elevenlabs]

You’ll also need to set up your ElevenLabs API key as an environment variable: ELEVENLABS_API_KEY.

​

Configuration

​

Constructor Parameters

​

Input Parameters

class InputParams(BaseModel):
    language: Optional[Language] = Language.EN
    optimize_streaming_latency: Optional[str]
    stability: Optional[float]
    similarity_boost: Optional[float]
    style: Optional[float]
    use_speaker_boost: Optional[bool]

​

Voice Settings

Voice characteristics can be configured using:

​

Output Frames

​

Control Frames

​

Audio Frames

​

Usage Examples

​

Basic Usage

# Configure service
tts_service = ElevenLabsTTSService(
    api_key="your-api-key",
    voice_id="voice-id",
    output_format="pcm_24000",
    params=ElevenLabsTTSService.InputParams(
        language=Language.EN
    )
)

# Use in pipeline
pipeline = Pipeline([
    text_input,
    tts_service,
    audio_output
])

​

With Voice Settings

# Configure with voice customization
service = ElevenLabsTTSService(
    api_key="your-api-key",
    voice_id="voice-id",
    params=ElevenLabsTTSService.InputParams(
        stability=0.7,
        similarity_boost=0.8,
        style=0.5,
        use_speaker_boost=True
    )
)

​

Methods

See the TTS base class methods for additional functionality.

​

Language Support

ElevenLabs supports the following languages and their variants:

Note: Language support may vary based on the selected model.

​

Usage Example

# Configure service with specific language
service = ElevenLabsTTSService(
    api_key="your-api-key",
    voice_id="voice-id",
    params=ElevenLabsTTSService.InputParams(
        language=Language.FR  # French
    )
)

​

Word Timing

The service provides word-level timing information:

# Word timing calculation
word_times = calculate_word_times(
    alignment_info,
    cumulative_time
)

​

Frame Flow

​

Features

​

Sentence Aggregation

• Aggregates sentences for better audio quality
• Maintains natural speech flow
• Reduces artifacts

​

Word Timing

• Provides word-level timestamps
• Enables text-audio synchronization
• Supports interruption handling

​

Connection Management

• WebSocket-based streaming
• Automatic reconnection
• Keepalive handling
• Clean disconnection

​

Notes

• Supports real-time streaming
• Provides word-level timing
• Handles interruptions gracefully
• Maintains WebSocket connection
• Includes metrics collection
• Supports voice customization
• Thread-safe processing
• Automatic language mapping