Skip to main content

Smallest AI STT plugin guide

How to use the Smallest AI Pulse STT plugin for LiveKit Agents.

On this page

OverviewInstallationAuthenticationUsageParametersSpeaker diarization Additional resources
Available in
Python

Overview

This plugin allows you to use the Smallest AI Pulse platform as an STT provider for your voice agents.

Installation

Install the plugin from PyPI:

uv add "livekit-agents[smallestai]~=1.5"

Authentication

The Smallest AI plugin requires an API key.

Set SMALLEST_API_KEY in your .env file.

Usage

Use Smallest AI 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 smallestai


session = AgentSession(
    stt=smallestai.STT(
        language="en",
    ),
    # ... llm, tts, etc.
)

Parameters

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

modelstringDefault: pulse

The STT model to use. Currently pulse is the only available model.

languagestringDefault: en

Language code for the input audio. Set to multi to enable automatic language detection. See Smallest AI documentation for a complete list of supported languages.

word_timestampsboolDefault: true

Include per-word start and end timestamps and confidence scores in transcripts.

diarizeboolDefault: false

Set to true to enable speaker diarization.

eou_timeout_msintDefault: 0

Milliseconds of silence before the server considers an utterance complete and emits a final transcript. Set to 0 to disable server-side end-of-utterance detection, which is recommended when using LiveKit's built-in turn detection to minimize latency. Otherwise, supported values range from 100 to 10000.

Speaker diarization

To assign a speaker identifier to each transcribed word, set diarize=True. When enabled, each word includes a speaker ID and the STT reports capabilities.diarization=True.

from livekit.plugins import smallestai


session = AgentSession(
    stt=smallestai.STT(
        language="en",
        diarize=True,
    ),
    # ... llm, tts, etc.
)

To detect the primary speaker and format transcripts by speaker, see Speaker diarization and primary speaker detection.

Additional resources

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

Python

Python

PyPIReferenceGitHub

Smallest AI Pulse docs

Smallest AI's Pulse STT documentation.

Icon for Smallest AI TTS

Smallest AI TTS

Guide to the Smallest AI TTS plugin with LiveKit Agents.

Voice AI quickstart

Get started with LiveKit Agents and Smallest AI STT.