Speechmatics STT

Overview

Speechmatics speech-to-text is available in LiveKit Agents through LiveKit Inference and the Speechmatics plugin. With LiveKit Inference, your agent runs on LiveKit's infrastructure to minimize latency. No separate provider API key is required, and usage and rate limits are managed through LiveKit Cloud. Use the plugin instead if you want to manage your own billing and rate limits. Pricing for LiveKit Inference is available on the pricing page .

LiveKit Inference

Use LiveKit Inference to access Speechmatics STT without a separate Speechmatics API key.

Usage

To use Speechmatics, use the STT class from the inference module:

from livekit.agents import AgentSession, inference

session = AgentSession(
    stt=inference.STT(
        model="speechmatics/enhanced",
        language="en"
    ),
    # ... llm, tts, vad, turn_handling, etc.
)

import { AgentSession, inference } from '@livekit/agents';

session = new AgentSession({
    stt: new inference.STT({
        model: "speechmatics/enhanced",
        language: "en"
    }),
    // ... llm, tts, vad, turnHandling, etc.
});

Voice activity detection

Speechmatics doesn't detect end of speech server-side, so LiveKit Inference relies on a VAD running in your agent. The SDK runs the VAD on incoming audio locally, and when the speaker stops, it signals the LiveKit Inference gateway to flush the final transcript.

By default, the framework loads a Silero VAD for you. To use a different VAD, pass one with the vad parameter:

from livekit.agents import AgentSession, inference
from livekit.plugins import silero

session = AgentSession(
    stt=inference.STT(
        model="speechmatics/enhanced",
        vad=silero.VAD.load(),  # optional; the framework loads one if omitted
    ),
    # ... llm, tts, etc.
)

import { AgentSession, inference } from '@livekit/agents';
import * as silero from '@livekit/agents-plugin-silero';

session = new AgentSession({
    stt: new inference.STT({
        model: "speechmatics/enhanced",
        vad: await silero.VAD.load(),  // optional; the framework loads one if omitted
    }),
    // ... llm, tts, etc.
});

Parameters

Model parameters

Pass the following parameters inside extra_kwargs (Python) or modelOptions (Node.js):

For more details on these options, see the Speechmatics real-time API reference .

Plugin

The Speechmatics plugin connects directly to the Speechmatics API with your own API key. The plugin is available for Python only; for Node.js, use LiveKit Inference.

Installation

Install the plugin from PyPI:

uv add "livekit-agents[speechmatics,silero]~=1.5"

Authentication

The Speechmatics plugin requires an API key .

Set SPEECHMATICS_API_KEY in your .env file.

Usage

Use Speechmatics STT in an AgentSession or as a standalone transcription service. For example, you can use this STT in the Voice AI quickstart.

from livekit.plugins import speechmatics

session = AgentSession(
    stt=speechmatics.STT(),
    # ... llm, tts, etc.
)

Turn detection

The turn_detection_mode parameter sets which component detects the end of a turn. It supports four modes:

The default EXTERNAL mode needs no extra configuration, as shown in the Usage example.

To have Speechmatics detect the end of a turn instead, set turn_detection_mode to ADAPTIVE, SMART_TURN, or FIXED, and set turn_detection="stt" in the turn handling options:

from livekit.agents import AgentSession, TurnHandlingOptions
from livekit.plugins import speechmatics

session = AgentSession(
    stt=speechmatics.STT(
        turn_detection_mode=speechmatics.TurnDetectionMode.ADAPTIVE,
    ),
    turn_handling=TurnHandlingOptions(
        turn_detection="stt",
    ),
    # ... llm, tts, etc.
)

Parameters

This section describes the key parameters for the Speechmatics STT plugin. See the plugin reference for a complete list of all available parameters.

Speaker diarization

You can enable speaker diarization to attribute speech to individual speakers. When enabled, the STT reports capabilities.diarization = True, and the transcription output can include speaker information through the speaker_id and text attributes.

With diarization enabled, wrap the Speechmatics STT with MultiSpeakerAdapter to detect the primary speaker and format transcripts by speaker.

Enable diarization in the STT constructor. LiveKit Inference uses a string diarization mode, while the plugin uses the boolean enable_diarization:

stt = inference.STT(
    model="speechmatics/enhanced",
    extra_kwargs={
        # "none", "speaker", "channel", or "channel_and_speaker"
        "diarization": "speaker",
    },
)

stt = speechmatics.STT(
    enable_diarization=True,
    speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
)

Additional resources

The following resources provide more information about using Speechmatics with LiveKit Agents.

Python package

The livekit-plugins-speechmatics package on PyPI.

Plugin reference

Reference for the Speechmatics STT plugin.

GitHub repo

View the source or contribute to the LiveKit Speechmatics STT plugin.

Speechmatics docs

Speechmatics STT docs.