Simplismart STT plugin guide | LiveKit Documentation

Available in

Python

Overview

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

This section provides a brief overview of the Simplismart STT plugin. For more information, see Additional resources.

Install the plugin from PyPI:

uv add "livekit-agents[simplismart]~=1.3"

The Simplismart plugin requires a Simplismart API key.

Set SIMPLISMART_API_KEY in your .env file.

Use Simplismart 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 simplismart

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

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

modelstr | STTModelsOptionalDefault: openai/whisper-large-v3-turbo

Model identifier for the backend STT model. Examples include openai/whisper-large-v3-turbo. See plugin reference for full list.

languagestrOptionalDefault: en

Language code for transcription (default: "en").

taskLiteral['transcribe', 'translate']OptionalDefault: transcribe

Operation to perform. transcribe converts speech to text in the original language, and translate translates into English.

without_timestampsboolOptionalDefault: true

If true, disables timestamp generation in transcripts.

min_speech_duration_msintOptionalDefault: 0

Minimum duration (ms) for a valid speech segment.

temperaturefloatOptionalDefault: 0.0

Decoding temperature (affects randomness).

multilingualboolOptionalDefault: false

Whether to permit multilingual recognition.

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

The livekit-plugins-simplismart package on PyPI.

Reference for the Simplismart STT plugin.

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

Simplismart's documentation.

Get started with LiveKit Agents and Simplismart.