Google

​

Overview

GoogleSTTService provides real-time speech-to-text capabilities using Google Cloud’s Speech-to-Text V2 API. It supports interim results, multiple languages, and voice activity detection (VAD).

​

Installation

To use GoogleSTTService, install the required dependencies:

pip install pipecat-ai[google]

You’ll need Google Cloud credentials either as a JSON string or file.

​

Configuration

​

Constructor Parameters

​

InputParams

The InputParams class provides configuration options for the Google STT service.

​

Input

The service processes raw audio data with:

• Linear16 PCM encoding
• 16-bit depth
• Configurable sample rate
• Single channel (mono)

​

Output Frames

The service produces two types of frames:

​

TranscriptionFrame

Generated for final transcriptions, containing:

​

InterimTranscriptionFrame

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

​

Methods

async def set_languages(language: List[Language]) -> None

await service.set_languages([Language.FR_FR])

async def set_model(model: str) -> None

await service.set_model("medical_dictation")

async def update_options(
    *,
    languages: Optional[List[Language]] = None,
    model: Optional[str] = None,
    enable_automatic_punctuation: Optional[bool] = None,
    enable_spoken_punctuation: Optional[bool] = None,
    enable_spoken_emojis: Optional[bool] = None,
    profanity_filter: Optional[bool] = None,
    enable_word_time_offsets: Optional[bool] = None,
    enable_word_confidence: Optional[bool] = None,
    enable_interim_results: Optional[bool] = None,
    enable_voice_activity_events: Optional[bool] = None,
    location: Optional[str] = None,
) -> None

await service.update_options(
    languages=[Language.ES_ES, Language.EN_US],
    enable_interim_results=True,
    profanity_filter=True
)

See the STT base class methods for additional functionality.

​

Usage Example

from pipecat.services.google import GoogleSTTService
from pipecat.transcriptions.language import Language

# Configure service
stt_service = GoogleSTTService(
    credentials_path="path/to/credentials.json",
    params=GoogleSTTService.InputParams(
        languages=Language.EN_US,
        model="latest_long",
        enable_automatic_punctuation=True,
        enable_interim_results=True
    )
)

# Use in pipeline
pipeline = Pipeline([
    transport.input(),
    stt,
    context_aggregator.user(),
    llm,
    ...
])

​

Regional Support

Google Cloud Speech-to-Text V2 supports different regional endpoints for improved latency and data residency requirements.

​

Available Regions

See supported languages, models, and features for each region in Google’s Speech-to-Text documentation.

​

Configuration

Specify the region during service initialization:

stt_service = GoogleSTTService(
    credentials=credentials,
    location="us-central1",  # Use us-central1 endpoint
    params=GoogleSTTService.InputParams(
        model="chirp_2"
    )
)

​

Dynamic Region Updates

The region can be updated during runtime:

await stt_service.update_options(
    location="asia"
)

​

Notes

• The global endpoint is used by default
• Regional endpoints may provide lower latency for users in those regions
• Some features or models might only be available in specific regions
• Regional selection may affect pricing
• Data residency requirements may dictate region selection

​

Models

See Google Cloud’s Speech-to-Text documentation for more details.

​

Language Support

​

Special Features

• Supports multiple languages simultaneously
• Provides regional variants for many languages
• Handles different Chinese scripts (simplified/traditional)
• Supports medical-specific models

​

Frame Flow

​

Notes

• Requires Google Cloud credentials
• Supports real-time transcription
• Handles streaming connection management
• Provides dynamic configuration updates
• Supports model switching
• Includes VAD capabilities
• Manages connection lifecycle