Gladia Speech-to-Text

Overview

GladiaSTTService provides real-time speech recognition using Gladia’s WebSocket API with support for 99+ languages, custom vocabulary, translation, sentiment analysis, and advanced audio processing features for comprehensive transcription.

Gladia STT API Reference

Pipecat’s API methods for Gladia STT integration

Example Implementation

Complete example with interruption handling

Gladia Documentation

Official Gladia documentation and features

Gladia Platform

Access multilingual transcription and API keys

Installation

To use Gladia services, install the required dependency:

uv add "pipecat-ai[gladia]"

Prerequisites

Gladia Account Setup

Before using Gladia STT services, you need:

Gladia Account: Sign up at Gladia
API Key: Generate an API key from your account dashboard
Region Selection: Choose your preferred region (EU-West or US-West)

Required Environment Variables

GLADIA_API_KEY: Your Gladia API key for authentication

Configuration

GladiaSTTService

str

required

Gladia API key for authentication.

Literal['us-west', 'eu-west']

default:"None"

Region used to process audio. Defaults to "eu-west" when None.

str

default:"https://api.gladia.io/v2/live"

Gladia API URL for session initialization.

str

default:"wav/pcm"

Audio encoding format.

int

default:"16"

Audio bit depth.

int

default:"1"

Number of audio channels.

int

default:"None"

Audio sample rate in Hz. When None, uses the pipeline’s configured sample rate.

str

default:"None"

deprecated

Deprecated since 0.0.105, removed in 2.0.0. Use settings=GladiaSTTService.Settings(...) instead.

GladiaInputParams

default:"None"

deprecated

Deprecated since 0.0.105, removed in 2.0.0. Use settings=GladiaSTTService.Settings(...) instead.

GladiaSTTService.Settings

default:"None"

Settings for the STT service. See Settings below.

int

default:"20971520"

Maximum size of audio buffer in bytes (default 20MB).

bool

default:"True"

Whether the bot should be interrupted when Gladia VAD detects user speech. See User Turn Strategies if you pass your own user_turn_strategies.

float

default:"1.49"

P99 latency from speech end to final transcript in seconds. Override for your deployment. See stt-benchmark.

Settings

Settings passed via the settings constructor argument using GladiaSTTService.Settings(...). Changes sent with STTUpdateSettingsFrame aren’t applied at runtime: the session keeps the settings it was opened with. See Service Settings for details.

Parameter	Type	Default	Description
`model`	`str`	`"solaria-1"`	STT model identifier. (Inherited from base STT settings.)
`language`	`Language \| str`	`None`	Language for speech recognition. Not sent by this service, so it has no effect. Use `language_config` instead. (Inherited from base STT settings.)
`language_config`	`LanguageConfig`	`None`	Detailed language configuration with code switching support.
`custom_metadata`	`dict[str, Any]`	`None`	Additional metadata to include with requests.
`endpointing`	`float`	`None`	Silence duration in seconds to mark end of speech.
`maximum_duration_without_endpointing`	`int`	`5`	Maximum utterance duration (seconds) without silence.
`pre_processing`	`PreProcessingConfig`	`None`	Audio pre-processing options (audio enhancer, speech threshold).
`realtime_processing`	`RealtimeProcessingConfig`	`None`	Real-time processing features (custom vocabulary, translation, NER, sentiment).
`messages_config`	`MessagesConfig`	`None`	WebSocket message filtering options.
`enable_vad`	`bool`	`False`	Enable Gladia VAD for end-of-utterance detection. Use without other VAD in the agent.

Usage

Basic Setup

import os

from pipecat.services.gladia.stt import GladiaSTTService

stt = GladiaSTTService(
    api_key=os.getenv("GLADIA_API_KEY"),
)

With Language Configuration

from pipecat.services.gladia.stt import GladiaSTTService
from pipecat.services.gladia.config import LanguageConfig

stt = GladiaSTTService(
    api_key=os.getenv("GLADIA_API_KEY"),
    region="us-west",
    settings=GladiaSTTService.Settings(
        model="solaria-1",
        language_config=LanguageConfig(
            languages=["en", "es"],
            code_switching=True,
        ),
    ),
)

With Real-time Processing

from pipecat.services.gladia.stt import GladiaSTTService
from pipecat.services.gladia.config import (
    RealtimeProcessingConfig,
    CustomVocabularyConfig,
    CustomVocabularyItem,
    TranslationConfig,
)

stt = GladiaSTTService(
    api_key=os.getenv("GLADIA_API_KEY"),
    settings=GladiaSTTService.Settings(
        realtime_processing=RealtimeProcessingConfig(
            custom_vocabulary=True,
            custom_vocabulary_config=CustomVocabularyConfig(
                vocabulary=[
                    CustomVocabularyItem(value="Pipecat", intensity=0.8),
                    "Gladia",
                ],
            ),
            translation=True,
            translation_config=TranslationConfig(
                target_languages=["fr", "de"],
                model="enhanced",
            ),
        ),
    ),
)

Notes

Session-based connection: Gladia uses a two-step connection process: first an HTTP POST to initialize a session, then a WebSocket connection to the returned session URL. The session URL and ID are managed automatically.
Audio buffering: The service buffers audio data locally and sends it when connected. If the connection drops and reconnects, buffered audio is automatically re-sent to minimize transcript gaps.
Keepalive: Empty audio chunks are sent periodically to keep the Gladia connection alive (keepalive interval: 5s, timeout: 20s).
Built-in VAD: Set enable_vad=True in Settings to use Gladia’s server-side VAD. The service proposes each turn boundary and automatically requests ExternalUserTurnStrategies, which resolve those proposals into UserStartedSpeakingFrame and UserStoppedSpeakingFrame, so you don’t need to configure turn strategies manually. Pass your own user_turn_strategies only to override this. When using Gladia’s VAD, do not enable another VAD in your pipeline.
Translation: Gladia supports real-time translation to multiple target languages. Translation results are pushed as TranslationFrames.

Event Handlers

Gladia STT supports the standard service connection events:

Event	Description
`on_connected`	Connected to Gladia WebSocket
`on_disconnected`	Disconnected from Gladia WebSocket

@stt.event_handler("on_connected")
async def on_connected(service):
    print("Connected to Gladia")

Get Started

Pipecat Server

Client SDKs

Pipecat Flows

Pipecat Cloud

CLI

Pipecat Context Hub

Gladia Speech-to-Text

Overview

Gladia STT API Reference

Example Implementation

Gladia Documentation

Gladia Platform

Installation

Prerequisites

Gladia Account Setup

Required Environment Variables

Configuration

GladiaSTTService

Settings

Usage

Basic Setup

With Language Configuration

With Real-time Processing

Notes

Event Handlers

​Overview

Gladia STT API Reference

Example Implementation

Gladia Documentation

Gladia Platform

​Installation

​Prerequisites

​Gladia Account Setup

​Required Environment Variables

​Configuration

​GladiaSTTService

​Settings

​Usage

​Basic Setup

​With Language Configuration

​With Real-time Processing

​Notes

​Event Handlers

Overview

Installation

Prerequisites

Gladia Account Setup

Required Environment Variables

Configuration

GladiaSTTService

Settings

Usage

Basic Setup

With Language Configuration

With Real-time Processing

Notes

Event Handlers