Inworld TTS | LiveKit Documentation

Create a new agent in your browser using this model

Overview

Inworld text-to-speech is available in LiveKit Agents through LiveKit Inference and the Inworld plugin. With LiveKit Inference, your agent runs on LiveKit's infrastructure to minimize latency. No separate provider API key is required, and usage and rate limits are managed through LiveKit Cloud. Use the plugin instead if you want to manage your own billing and rate limits. Pricing for LiveKit Inference is available on the pricing page.

LiveKit Inference

Use LiveKit Inference to access Inworld TTS without a separate Inworld API key.

Model name	Model ID	Languages
Inworld TTS 1	inworld/inworld-tts-1	enesfrkonlzhdeitjaplptruhihear
Inworld TTS 1 Max	inworld/inworld-tts-1-max	enesfrkonlzhdeitjaplptruhihear
Inworld TTS 1.5 Max	inworld/inworld-tts-1.5-max	enzhjakoruitesptfrdeplnlhihear
Inworld TTS 1.5 Mini	inworld/inworld-tts-1.5-mini	enzhjakoruitesptfrdeplnlhihear

Usage

To use Inworld, use the TTS class from the inference module:

from livekit.agents import AgentSession, inference

session = AgentSession(
    tts=inference.TTS(
        model="inworld/inworld-tts-1.5-max", 
        voice="Ashley", 
        language="en"
    ),
    # ... llm, stt, vad, turn_handling, etc.
)

import { AgentSession, inference } from '@livekit/agents';

session = new AgentSession({
    tts: new inference.TTS({
        model: "inworld/inworld-tts-1.5-max",
        voice: "Ashley", 
        language: "en" 
    }),
    // ... llm, stt, vad, turnHandling, etc.
});

Parameters

model

Required

string

The model ID from the models list.

voice

Required

string

See voices for guidance on selecting a voice.

languageLanguageCode

Language code for the input text. If not set, the model default applies.

extra_kwargsdict

Additional parameters to pass to the Inworld TTS API. See model parameters for supported fields.

In Node.js this parameter is called modelOptions.

Model parameters

Pass the following parameters inside extra_kwargs (Python) or modelOptions (Node.js):

Parameter	Type	Notes
`speaking_rate`	`float`	Speaking rate multiplier. `1.0` is normal speed. Valid range: `0.5`–`1.5`.
`temperature`	`float`	Controls randomness in the generated voice. Higher values produce more variation. Valid range: `0`–`2`.
`timestamp_type`	`"TIMESTAMP_TYPE_UNSPECIFIED" \| "WORD" \| "CHARACTER"`	Granularity of timestamps returned with the audio.
`apply_text_normalization`	`"APPLY_TEXT_NORMALIZATION_UNSPECIFIED" \| "ON" \| "OFF"`	Whether to normalize text before synthesis (expand numbers, abbreviations, etc.).

Voices

LiveKit Inference supports all of the default voices available in the Inworld API. You can explore the available voices in the Inworld TTS Playground (free account required), and use the voice by copying its name into your LiveKit agent session.

Cloned voices unavailable

Cloned voices are not yet supported in LiveKit Inference. To use these voices, create your own Inworld account and use the Inworld plugin for LiveKit Agents instead.

The following is a small sample of the Inworld voices available in LiveKit Inference.

Use the keyboard and arrows to audition voices

String descriptors

As a shortcut, you can also pass a descriptor with the model ID and voice directly to the tts argument in your AgentSession:

from livekit.agents import AgentSession

session = AgentSession(
    tts="inworld/inworld-tts-1.5-max:Ashley",
    # ... llm, stt, vad, turn_handling, etc.
)

import { AgentSession } from '@livekit/agents';

session = new AgentSession({
    tts: "inworld/inworld-tts-1.5-max:Ashley",
    // ... llm, stt, vad, turnHandling, etc.
});

Plugin

LiveKit's plugin support for Inworld lets you connect directly to Inworld's TTS API with your own API key.

Available in

Python

Node.js

Installation

Install the plugin from PyPI:

uv add "livekit-agents[inworld]~=1.4"

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

Authentication

The Inworld plugin requires a Base64-encoded Inworld API key.

Set INWORLD_API_KEY in your .env file.

Usage

Use Inworld TTS within an AgentSession or as a standalone speech generator. For example, you can use this TTS in the Voice AI quickstart.

from livekit.plugins import inworld

session = AgentSession(
   tts=inworld.TTS(model="inworld-tts-1.5-max", voice="Ashley")
   # ... llm, stt, etc.
)

import * as inworld from '@livekit/agents-plugin-inworld';

const session = new voice.AgentSession({
    tts: inworld.TTS(
        model: "inworld-tts-1.5-max",
        voice: "Ashley",
    ),
    // ... llm, stt, etc.
});

Parameters

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

modelstringDefault: "inworld-tts-1.5-max"

ID of the model to use for generation. See supported models.

voicestringDefault: "Ashley"

ID of the voice to use for generation. Use the List voices API endpoint for possible values.

temperaturefloatDefault: 1.1

Controls randomness in the output. Recommended to set between 0.6 and 1.1. See docs.

speaking_ratefloatDefault: 1.0

Controls how fast the voice speaks. 1.0 is the normal native speed, while 0.5 is half the normal speed and 1.5 is 1.5x faster than the normal speed. See docs.

text_normalizationstringDefault: ON

Controls text normalization. When "ON", numbers, dates, and abbreviations are expanded (e.g., "Dr." -> "Doctor"). When "OFF", text is read exactly as written. See docs.

Customizing pronunciation

Inworld TTS supports customizing pronunciation. To learn more, see Custom Pronunciation guide.

Additional resources

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

Python package

The livekit-plugins-inworld package on PyPI.

Plugin reference

Reference for the Inworld TTS plugin.

GitHub repo

View the source or contribute to the LiveKit Inworld TTS plugin.

Inworld docs

Inworld TTS docs.