CLOVA STT integration guide

How to use the Clova STT plugin for LiveKit Agents.

Overview

CLOVA Speech Recognition is the NAVER Cloud Platform's service to convert human voice into text. You can use the open source CLOVA plugin for LiveKit Agents to build voice AI with fast, accurate transcription.

Quick reference

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

Installation

Install the plugin from PyPI:

pip install "livekit-agents[clova]~=1.0"

Authentication

The CLOVA plugin requires the following keys, which may set as environment variables or passed to the constructor.

CLOVA_STT_SECRET_KEY=<your-api-key>
CLOVA_STT_INVOKE_URL=<your-invoke-url>

Usage

Create a CLOVA STT to use within an AgentSession or as a standalone transcription service. For example, you can use this STT in the Voice AI quickstart.

from livekit.plugins import clova
session = AgentSession(
stt = clova.STT(
word_boost=["LiveKit"],
),
# ... llm, tts, etc.
)

Parameters

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

languageClovaSttLanguagesOptionalDefault: en-US

Speech recognition language. Clova supports English, Korean, Japanese, and Chinese. Valid values are ko-KR, en-US, enko, ja, zh-cn, zh-tw.

Additional resources

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

Voice AI quickstart

Get started with LiveKit Agents and CLOVA.