AssemblyAI TTS

Overview

AssemblyAI text-to-speech is available in LiveKit Agents through LiveKit Inference and the AssemblyAI 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 AssemblyAI TTS without a separate AssemblyAI API key.

Usage

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

from livekit.agents import AgentSession, inference

session = AgentSession(
    tts=inference.TTS(
        model="assemblyai/assemblyai-tts-1",
        voice="49c443a4-8a1d-5f7e-b70b-98bdbd9823c3",  # Audrey
        language="en"
    ),
    # ... llm, stt, vad, turn_handling, etc.
)

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

const session = new AgentSession({
    tts: new inference.TTS({
        model: "assemblyai/assemblyai-tts-1",
        voice: "49c443a4-8a1d-5f7e-b70b-98bdbd9823c3", // Audrey
        language: "en"
    }),
    // ... llm, stt, vad, turnHandling, etc.
});

Parameters

Model parameters

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

Voices

LiveKit Inference supports the voices in the AssemblyAI voice library . To use a voice, copy its ID from the voice library into your agent session.

Each voice is recorded in one language. A voice can speak any supported language, but it keeps the accent of its recording, so pick a voice recorded in the language of your text and set language to match.

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="assemblyai/assemblyai-tts-1:49c443a4-8a1d-5f7e-b70b-98bdbd9823c3",
    # ... llm, stt, vad, turn_handling, etc.
)

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

const session = new AgentSession({
    tts: "assemblyai/assemblyai-tts-1:49c443a4-8a1d-5f7e-b70b-98bdbd9823c3",
    // ... llm, stt, vad, turnHandling, etc.
});

Plugin

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

Installation

Install the plugin:

uv add "livekit-agents[assemblyai]~=1.8"

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

Authentication

The AssemblyAI plugin requires an AssemblyAI API key .

Set ASSEMBLYAI_API_KEY in your .env file.

Usage

Use AssemblyAI 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 assemblyai

session = AgentSession(
    tts=assemblyai.TTS(
        model="assemblyai-tts-1",
        voice="49c443a4-8a1d-5f7e-b70b-98bdbd9823c3",  # Audrey
    ),
    # ... llm, stt, etc.
)

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

const session = new voice.AgentSession({
    tts: new assemblyai.TTS({
        model: "assemblyai-tts-1",
        voice: "49c443a4-8a1d-5f7e-b70b-98bdbd9823c3", // Audrey
    }),
    // ... llm, stt, etc.
});

The plugin keeps a pool of open websocket sessions and reuses them across replies. To open a session before the agent's first reply, call prewarm() on the TTS instance.

Parameters

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

To change the voice, language, or model during a session, call update_options() (Python) or updateOptions() (Node.js). A reply that's already playing keeps its voice until it finishes.

Transcription timing

AssemblyAI TTS returns per-word timings by default, which LiveKit uses to sync the agent's transcript with its speech and to record how much of an interrupted reply the user heard. Set use_tts_aligned_transcript=True in your AgentSession configuration to use them. To learn more, see the docs.

Additional resources

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

Python

ReferenceGitHubPyPI

Node.js

ReferenceGitHubNPM

AssemblyAI docs

AssemblyAI's docs for Streaming TTS.

AssemblyAI STT

Guide to using AssemblyAI STT with LiveKit Agents.