Spitch STT plugin guide

Available in

Python

Overview

This plugin allows you to use Spitch as an STT provider for your voice agents.

This section provides a quick reference for the Spitch STT plugin. For more information, see Additional resources.

Install the plugin from PyPI:

uv add "livekit-agents[spitch]~=1.2"

The Spitch plugin requires a Spitch API key.

Set SPITCH_API_KEY in your .env file.

Use Spitch 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 spitch

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

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

languagestringOptionalDefault: en

Language short code of the input speech. For supported values, see Spitch languages.

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

The livekit-plugins-spitch package on PyPI.

Reference for the Spitch STT plugin.

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

Spitch's official documentation.

Get started with LiveKit Agents and Spitch.

Guide to the Spitch TTS plugin with LiveKit Agents.