Deepgram

​

Overview

DeepgramSTTService provides real-time speech-to-text capabilities using Deepgram’s WebSocket API. It supports interim results, language detection, and voice activity detection (VAD).

​

Installation

To use DeepgramSTTService, install the required dependencies:

pip install pipecat-ai[deepgram]

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

​

Configuration

​

Constructor Parameters

​

Default Options

LiveOptions(
    encoding="linear16",
    language=Language.EN,
    model="nova-2-general",
    sample_rate=16000,
    channels=1,
    interim_results=True,
    smart_format=True,
    punctuate=True,
    profanity_filter=True,
    vad_events=False
)

​

Input

The service processes InputAudioRawFrame instances containing:

• Raw PCM audio data
• 16-bit depth
• 16kHz sample rate
• Single channel (mono)

​

Output Frames

The service produces two types of frames during transcription:

​

TranscriptionFrame

Generated for final transcriptions, containing:

​

InterimTranscriptionFrame

Generated during ongoing speech, containing same fields as TranscriptionFrame but with preliminary results.

​

Methods

See the STT base class methods for additional functionality.

​

Language Setting

await service.set_language(Language.FR)

​

Model Selection

await service.set_model("nova-2-general")

​

Usage Example

from pipecat.services.deepgram import DeepgramSTTService
from deepgram import LiveOptions

# Configure service
stt_service = DeepgramSTTService(
    api_key="your-api-key",
    live_options=LiveOptions(
        model="nova-2-general",
        language="en-US",
        smart_format=True,
        vad_events=True
    )
)

# Use in pipeline
pipeline = Pipeline([
    transport.input(),   # Produces InputAudioRawFrame
    stt_service,         # Processes audio → produces transcription frames
    text_handler         # Consumes transcription frames
])

​

Language Support

Deepgram STT supports the following languages and regional variants:

​

Special Features

• Supports multilingual transcription (Spanish + English) using multi
• Provides multiple regional variants for major languages
• Supports traditional and simplified Chinese scripts

​

Usage Example

# Configure service with specific language
stt_service = DeepgramSTTService(
    api_key="your-api-key",
    live_options=LiveOptions(
        language="en-US",  # Specific regional variant
        model="nova-2-general"
    )
)

Note: Language support may vary by model. Check Deepgram’s documentation for model-specific language availability.

​

Frame Flow

​

Metrics Support

The service supports metrics collection when VAD is enabled:

• Time to First Byte (TTFB)
• Processing duration
• Speech detection events

​

Notes

• Requires valid Deepgram API key
• Supports real-time transcription
• Handles WebSocket connection management
• Provides language detection
• Supports model switching
• Includes VAD capabilities
• Manages connection lifecycle