LiveKit docs › Models › STT › Additional models › Inworld

---

# Inworld STT plugin guide

> How to use the Inworld STT plugin for LiveKit Agents.

Available in:
- [x] Node.js
- [x] Python

## Overview

This plugin allows you to use [Inworld](https://inworld.ai/) as an STT provider for your voice agents.

### Installation

Install the plugin:

**Python**:

```shell
uv add "livekit-agents[inworld]~=1.5"

```

---

**Node.js**:

```shell
pnpm add @livekit/agents-plugin-inworld@1.x

```

### Authentication

The Inworld plugin requires a Base64-encoded [Inworld API key](https://platform.inworld.ai/login).

Set `INWORLD_API_KEY` in your `.env` file.

### Usage

Use Inworld STT in an `AgentSession` or as a standalone transcription service. For example, you can use this STT in the [Voice AI quickstart](https://docs.livekit.io/agents/start/voice-ai.md).

**Python**:

```python
from livekit.agents import AgentSession
from livekit.plugins import inworld

session = AgentSession(
   stt=inworld.STT(
      model="inworld/inworld-stt-1",
      language="en-US",
   ),
   # ... llm, tts, etc.
)

```

---

**Node.js**:

```typescript
import { voice } from '@livekit/agents';
import * as inworld from '@livekit/agents-plugin-inworld';

const session = new voice.AgentSession({
    stt: new inworld.STT({
        model: "inworld/inworld-stt-1",
        language: "en-US",
    }),
    // ... llm, tts, etc.
});

```

### Parameters

This section describes commonly used parameters. See the plugin reference links in the [Additional resources](#additional-resources) section for a complete list of all available parameters.

- **`model`** _(string)_ (optional) - Default: `inworld/inworld-stt-1`: The Inworld STT model to use. Inworld serves several models through the same API, including `inworld/inworld-stt-1`, `assemblyai/universal-streaming-multilingual`, and `soniox/stt-rt-v4`. See the [Inworld STT docs](https://docs.inworld.ai/docs/stt) for the current list of supported models.

- **`language`** _(LanguageCode)_ (optional) - Default: `en-US`: [Language code](https://docs.livekit.io/agents/models/stt.md#language-codes) for the input audio. See the [Inworld STT docs](https://docs.inworld.ai/docs/stt) for supported languages.

- **`sample_rate`** _(integer)_ (optional) - Default: `16000`: Input audio sample rate in Hz.

- **`num_channels`** _(integer)_ (optional) - Default: `1`: Number of audio channels in the input stream.

- **`enable_voice_profile`** _(boolean)_ (optional) - Default: `true`: Enables voice profiling, which detects speaker characteristics such as age, gender, emotion, and accent on each transcript.

- **`voice_profile_top_n`** _(integer)_ (optional) - Default: `1`: Number of top voice profile results to return per category when `enable_voice_profile` is set.

- **`vad_threshold`** _(float)_ (optional): Voice activity detection sensitivity. If unset, Inworld applies its own default.

- **`min_end_of_turn_silence_when_confident`** _(integer)_ (optional) - Default: `200`: Minimum silence, in milliseconds, required to end a turn when the model is confident the speaker has finished.

- **`end_of_turn_confidence_threshold`** _(float)_ (optional) - Default: `0.3`: Confidence threshold used to decide when a turn has ended.

Valid range: `0.0`–`1.0`

## Additional resources

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

- **[Inworld STT docs](https://docs.inworld.ai/docs/stt)**: Inworld's speech-to-text documentation.

- **[Voice AI quickstart](https://docs.livekit.io/agents/start/voice-ai.md)**: Get started with LiveKit Agents and Inworld STT.

- **[Inworld TTS](https://docs.livekit.io/agents/models/tts/inworld.md)**: Guide to the Inworld TTS plugin with LiveKit Agents.

---

This document was rendered at 2026-06-07T11:35:47.542Z.
For the latest version of this document, see [https://docs.livekit.io/agents/models/stt/inworld.md](https://docs.livekit.io/agents/models/stt/inworld.md).

To explore all LiveKit documentation, see [llms.txt](https://docs.livekit.io/llms.txt).