elevenlabs-convai {
    --el-bg-color: rgb(var(--background-light));
    --el-text-color: rgb(var(--gray-700));
    --el-border-color: rgb(var(--gray-400) / 0.2);
    --el-border-radius: 0.75rem;
    --el-btn-color: rgb(var(--primary-dark));
    --el-btn-text-color: #fff;
    --el-btn-radius: 32px;
    --el-focus-color: rgb(var(--primary-light));
}

.dark elevenlabs-convai {
    --el-bg-color: rgb(var(--background-dark));
    --el-text-color: rgb(var(--gray-300));
    --el-border-color: rgb(var(--gray-800));
    --el-border-radius: 0.75rem;
    --el-btn-color: rgb(var(--primary-light) / 0.1);
    --el-btn-text-color: rgb(var(--primary-light));
    --el-btn-radius: 32px;
    --el-focus-color: rgb(var(--primary-light));
}


(function() {
  // Create and append the script element
  var script = document.createElement('script');
  script.src = "https://elevenlabs.io/convai-widget/index.js";
  script.async = true;
  script.type = "text/javascript";
  document.head.appendChild(script);

  // hide convai on mobile
  var wrapper = document.createElement('div');
  wrapper.className = "hidden lg:block";

  // Create and append the widget element
  var widget = document.createElement('elevenlabs-convai');
  widget.setAttribute('agent-id', 'oapIEuaQlE30RdjtC9BX');
  widget.setAttribute('avatar-orb-color-1', '#4D9CFF');
  widget.setAttribute('avatar-orb-color-2', '#9CE6E6');
  widget.innerHTML = `\
  <form slot="terms" class="prose text-sm">
    <h3>Terms and conditions</h3>
    <p>
      By clicking "Continue," I agree to the Terms of Service, acknowledge
      ElevenLabs' Privacy Policy.
    </p>
    <p>
      <label class="flex gap-2">
        <input class="h-5" required="required" type="checkbox" />
        I consent to the recording, collection and use of my voice and data
        derived from my voice to interpret my speech and provide customer
        support services.
      </label>
    </p>
    <p>
      <label class="flex gap-2">
        <input class="h-5" required="required" type="checkbox" />
        I consent to sharing my voice and data derived from my voice with 
        third-party service providers to train and improve our customer 
        support models.
      </label>
    </p>
    <p>
      <label class="flex gap-2">
        <input class="h-5" required="required" type="checkbox" />
        I understand that if I do not consent to the collection as 
        described above, ElevenLabs services cannot be provided to 
        me.
      </label>
    </p>
  </form>`;
  
  // Append widget to wrapper, then wrapper to body
  wrapper.appendChild(widget);
  document.body.appendChild(wrapper);
})();

Community

Documentation

ElevenLabs

product

Product

API Reference

Developer Guides

Conversational AI

Changelog

Go to elevenlabs.io

Blog

Help Center

Create Agent

Keywords

ASRConversationalConfig

First Message

Language

AgentConfig

Data Collection

AgentPlatformSettings

Enable Auth

AuthSettings

ClientEvent

Max Duration Seconds

ConversationConfig

ConversationalConfig

Action Text

Avatar

Bg Color

Border Color

Border Radius

Btn Color

Btn Radius

Btn Text Color

Custom Avatar Path

End Call Text

Expand Text

Focus Color

Listening Text

Speaking Text

Start Call Text

Text Color

EmbedConfig

EmbedVariant

Settings to evaluate an agent's performance.
Agents are evaluated against a set of criteria, with success being defined as meeting some combination of those criteria.

Criteria

EvaluationSettings

Type

ImageAvatar

JSON schema literal types. e.g. all Json types except nested objects and lists

JsonLiteralType

Description

LiteralJsonSchemaProperty

Color 1

Color 2

OrbAvatar

An evaluation using the transcript and a prompt for a yes/no achieved answer

Conversation Goal Prompt

Name

PromptEvaluationCriteria

Stability

Voice Id

TTSConversationalConfig

TTSConversationalModel

TTSOptimizeStreamingLatency

TTSOutputFormat

Turn Timeout

TurnConfig

Custom Url

URLAvatar

Location

Message

Error Type

ValidationError

Body_Create_Agent_v1_convai_agents_create_post

CreateAgentResponseModel

HTTPValidationError

Explore our Guides and API Reference to get the most out of ElevenLabs.

Introduction

A guide on how to generate voiceovers using your voice on ElevenLabs.

Overview

Voice Selection

Voice Settings

Model Selection

Effective techniques to guide ElevenLabs AI in adding pauses, conveying emotions, and pacing the speech.

Prompting

A guide on using our voice changer tool for the most natural-sounding speech-to-speech conversion

Get the most out of our Sound Effects Generator tool and learn how to create everything from blockbuster sound design for films to everyday sounds for your video game.

Discover all the voices ElevenLabs has to offer

A curated set of voices for our core use cases.

Default Voices

Generate a unique voice from a text prompt.

Voice Design

Guide for getting the most out of you cloned voices.

Instant Voice Cloning

Guide to getting the highest quality voice clone available.

Professional Voice Cloning

Discover AI voices from the ElevenLabs community

Learn how to share voices in the Voice Library.

Sharing Voices

Step-by-step guide to creating the highest quality voice clone available

Step-by-step Guide

Earn rewards for sharing voices in the Voice Library

Payouts

Dubbing made easy: reach a broader audience with ElevenLabs.

The ultimate end-to-end workflow for creating amazing dubs.

Studio

Elevate your projects with this guide into the Voiceover Studio.

An overview on how teams can collaborate in a shared workspace.

An overview on how to setup SSO (Single Sign-On) for your team.

SSO Setup

General troubleshooting guide and overview for some issues we've seen.

Start generating your first text-to-speech using Python and ElevenLabs API

Quickstart

How to control the server location for your requests

Specifying Server Location

Seven methods for reducing streaming latency, in order of highest to lowest effectiveness:

Reducing Latency

Models

How to convert text into speech, upload to S3, and share with a signed URL

How to Use Text-to-Speech

How to use text to speech with streaming in Python or Node.js

How to convert text to speech via websocket and save to mp3

Streaming Text-to-Speech

How to use text-to-speech with websocket streaming in Python or Node.js

Learn how to keep your voice stable across multiple generations

Combine Multiple Generations

How to add, view, and remove rules to pronunciation dictionaries with the Python SDK

How to Use Pronunciation Dictionaries

Integrating with Twilio

How to send an AI message through a phone call using Twilio and ElevenLabs in Node.js

Learn how to use the text to sound effects API to generate sound effects from text.

How to Use the Text to Sound Effects API

Learn how to automate the dubbing of audio and video files into various languages using the ElevenLabs API

How to Dub a Video

How to dub video and audio with ElevenLabs

Project Examples

Overview of ElevenLabs API endpoints and capabilities

API Reference Overview

Node Library

Python Library

API that converts text into lifelike speech with best-in-class latency & uses the most advanced AI audio model ever. Create voiceovers for your videos, audiobooks, or create AI chatbots for free.

Text To Speech

Converts text into audio together with timestamps on when which word was spoken.

Text To Speech With Timestamps

Converts text into speech using a voice of your choice and returns audio as an audio stream.

Text To Speech Streaming

Converts text into audio together with timestamps on when which word was spoken in a streaming way.

Text To Speech Streaming With Timestamps

Websockets

Use Speech to Speech API to transform uploaded speech so it sounds like it was spoken by another voice. STS gives you full control over the emotions, timing and delivery.

Speech To Speech

Create speech by combining the content and emotion of the uploaded audio with a voice of your choice and returns an audio stream.

Streaming

API that converts text into sounds & uses the most advanced AI audio model ever. Create sound effects for your videos, voice-overs or video games.

Sound Generation

Audio Isolation

Removes background noise from audio and streams the result

Audio Isolation Stream

Returns metadata about all your generated audio.

Get Generated Items

Returns information about an history item by its ID.

Get History Item By Id

Delete History Item

Get Audio From History Item

Download one or more history items. If one history item ID is provided, we will return a single audio file. If more than one history item IDs are provided, we will provide the history items packed into a .zip file.

Download History Items

Delete Sample

Returns the audio corresponding to a sample attached to a voice.

Get Audio From Sample

Gets extended information about the users subscription

Get User Subscription Info

Get User Info

Gets a list of all available voices for a user.

Get Voices

Gets the default settings for voices. "similarity_boost" corresponds to"Clarity + Similarity Enhancement" in the web app and "stability" corresponds to "Stability" slider in the web app.

Get Default Voice Settings.

Returns the settings for a specific voice. "similarity_boost" corresponds to"Clarity + Similarity Enhancement" in the web app and "stability" corresponds to "Stability" slider in the web app.

Get Voice Settings

Get Voice

Delete Voice

Edit your settings for a specific voice. "similarity_boost" corresponds to"Clarity + Similarity Enhancement" in the web app and "stability" corresponds to "Stability" slider in the web app.

Edit Voice Settings

Add a new voice to your collection of voices in VoiceLab.

Add Voice

Edit Voice

Generate custom voice previews based on provided voice description. The response includes a list of voice previews, each containing an id and a sample of the voice audio. If you like the voice preview and want to create a permanent voice, call `/v1/text-to-voice/create-voice-from-preview` with the corresponding voice id.

Generate Voice Previews From Description

Create a new voice from previously generated voice preview. This endpoint should be called after you fetched a `generated_voice_id` using `/v1/text-to-voice/create-previews`.

Create Voice From Voice Preview

Add a sharing voice to your collection of voices in VoiceLab.

Add Sharing Voice

Returns a list of your projects together and its metadata.

Get Projects

Returns information about a specific project. This endpoint returns more detailed information about a project than GET api.elevenlabs.io/v1/projects.

Get Project By Id

Creates a new project, it can be either initialized as blank, from a document or from a URL.

Quickstart

Customization

Libraries & SDKs

API Reference

Create Agent

Headers

Body

Response