​

Overview

AzureTTSService provides high-quality text-to-speech synthesis using Azure’s Cognitive Services. It supports SSML for advanced voice control and multiple languages.

​

Installation

To use AzureTTSService, install the required dependencies:

pip install "pipecat-ai[azure]"

You’ll also need to set up the following environment variables:

• AZURE_API_KEY
• AZURE_REGION

​

Configuration

​

Constructor Parameters

​

Input Parameters

class InputParams(BaseModel):
    emphasis: Optional[str]
    language: Optional[Language] = Language.EN_US
    pitch: Optional[str]
    rate: Optional[str] = "1.05"
    role: Optional[str]
    style: Optional[str]
    style_degree: Optional[str]
    volume: Optional[str]

​

Supported Sample Rates

• 8000 Hz: Raw8Khz16BitMonoPcm
• 16000 Hz: Raw16Khz16BitMonoPcm
• 22050 Hz: Raw22050Hz16BitMonoPcm
• 24000 Hz: Raw24Khz16BitMonoPcm
• 44100 Hz: Raw44100Hz16BitMonoPcm
• 48000 Hz: Raw48Khz16BitMonoPcm

​

Usage Example

# Configure service
tts = AzureTTSService(
    api_key="your-api-key",
    region="eastus",
    voice="en-US-JennyNeural",
    params=AzureTTSService.InputParams(
        language=Language.EN_US,
        rate="1.1",
        style="cheerful"
    )
)

# Use in pipeline
pipeline = Pipeline([
    ...,
    llm,
    tts,
    transport.output(),
])

​

Methods

See the TTS base class methods for additional functionality.

​

Language Support

Azure Speech Services support the following languages and regional variants:

​

Usage Examples

​

TTS Configuration

# Configure TTS with specific language
tts = AzureTTSService(
    api_key="your-api-key",
    region="eastus",
    params=AzureTTSService.InputParams(
        language=Language.FR_CA,  # Canadian French
        voice="fr-CA-SylvieNeural"
    )
)

​

Regional Considerations

• Each language code includes both language and region (e.g., fr-FR for French in France)
• Some languages have multiple regional variants (e.g., English has US, UK, Australian, Indian, and New Zealand variants)
• Voice availability may vary by region and language
• Neural voices are available for most language/region combinations
• Some features (like custom pronunciation) may be limited to specific languages

Note: Voice selection should match the specified language code for optimal results. Check Azure’s documentation for the latest list of available voices for each language/region combination.

​

SSML Support

The service supports rich SSML customization:

# Example with multiple SSML features
params = AzureTTSService.InputParams(
    emphasis="strong",
    pitch="+2st",
    rate="1.2",
    style="cheerful",
    style_degree="2",
    volume="loud"
)

​

Frame Flow

​

Metrics Support

The service collects processing metrics:

• Time to First Byte (TTFB)
• Processing duration
• Character usage
• API calls

​

Notes

• SSML-based speech customization
• Chunked audio delivery
• Thread-safe processing
• Automatic error handling
• Manages Azure client lifecycle