Quickstart

The ElevenLabs API provides a simple interface to state-of-the-art audio models and features. Follow this guide to learn how to create lifelike speech, generate and modify voices, produce immersive sound effects, isolate background noise from audio, and seamlessly dub audio/videos.

Create and export an API key

Create an API key in the dashboard here, which you’ll use to securely access the API. Store the key in a safe location, like a .zshrc file or another text file on your computer. Once you’ve generated an API key, export it as an environment variable in your terminal.

Export an environment variable on macOS or Linux systems

export ELEVENLABS_API_KEY="your_api_key_here"

Export an environment variable on macOS or Linux systems

export ELEVENLABS_API_KEY="your_api_key_here"

Export an environment variable in PowerShell

setx ELEVENLABS_API_KEY "your_api_key_here"

Make your first API request

With your ElevenLabs API key exported as an environment variable, you’re ready to make your first API request. You can either use the REST API directly with the HTTP client of your choice, or use one of our official SDKs as shown below.

To use the ElevenLabs API in server-side JavaScript environments like Node.js, Deno, or Bun, you can use the official ElevenLabs SDK for TypeScript and JavaScript. Get started by installing the SDK using npm or your preferred package manager:

Install the ElevenLabs SDK with npm

npm install elevenlabs

To play the audio through your speakers, you may be prompted to install MPV and/or ffmpeg.

With the ElevenLabs SDK installed, create a file called example.mjs and copy one of the following examples into it:

Convert text into life-like audio

import { ElevenLabsClient, play } from "elevenlabs";

const client = new ElevenLabsClient();
const audio = await client.textToSpeech.convert("JBFqnCBsd6RMkjVDRZzb", {
  text: "The first move is what sets everything in motion.",
  model_id: "eleven_multilingual_v2",
  output_format: "mp3_44100_128",
});

await play(audio);

Convert text into life-like audio

import { ElevenLabsClient, play } from "elevenlabs";

const client = new ElevenLabsClient();
const audio = await client.textToSpeech.convert("JBFqnCBsd6RMkjVDRZzb", {
  text: "The first move is what sets everything in motion.",
  model_id: "eleven_multilingual_v2",
  output_format: "mp3_44100_128",
});

await play(audio);

Transform audio from one voice to another

import { ElevenLabsClient, play } from "elevenlabs";
import fetch from "node-fetch";

const client = new ElevenLabsClient();
const voiceId = "JBFqnCBsd6RMkjVDRZzb";

const audioUrl = "https://storage.googleapis.com/eleven-public-cdn/audio/marketing/nicole.mp3";
const response = await fetch(audioUrl);
const audioBlob = new Blob([await response.arrayBuffer()], { type: "audio/mp3" });

const audioStream = await client.speechToSpeech.convert(voiceId, {
  audio: audioBlob,
  model_id: "eleven_multilingual_sts_v2",
  output_format: "mp3_44100_128",
});

await play(audioStream);

Convert text into sound effects

import { ElevenLabsClient, play } from "elevenlabs";

const client = new ElevenLabsClient();

const audio = await client.textToSoundEffects.convert({
  text: "Cinematic Braam, Horror",
});

await play(audio);

Removes background noise from audio.

import { ElevenLabsClient, play } from "elevenlabs";
import fetch from "node-fetch";

const client = new ElevenLabsClient();

const audioUrl =
  "https://storage.googleapis.com/eleven-public-cdn/audio/marketing/fin.mp3";
const response = await fetch(audioUrl);
const audioBlob = new Blob([await response.arrayBuffer()], {
  type: "audio/mp3",
});

const audioStream = await client.audioIsolation.audioIsolation({
  audio: audioBlob,
});

await play(audioStream);

Generate voices from a single text prompt.

import { ElevenLabsClient, play } from "elevenlabs";
import { Readable } from "stream";

const client = new ElevenLabsClient();

const voices = await client.textToVoice.createPreviews({
  voice_description: "A sassy squeaky mouse",
  text: "Every act of kindness, no matter how small, carries value and can make a difference, as no gesture of goodwill is ever wasted.",
});
const voicePreview1 = voices.previews[0].audio_base_64;

await play(Readable.from(Buffer.from(voicePreview1, "base64")));

Dub audio/video from one language to another

import { ElevenLabsClient, play } from "elevenlabs";
import fetch from "node-fetch";

const client = new ElevenLabsClient();

const targetLang = "es"; // spanish
const sourceAudio = await fetch(
  "https://storage.googleapis.com/eleven-public-cdn/audio/marketing/nicole.mp3"
);
const audioBlob = new Blob([await sourceAudio.arrayBuffer()], {
  type: "audio/mp3",
});

// Start dubbing
const dubbed = await client.dubbing.dubAVideoOrAnAudioFile({
  file: audioBlob,
  target_lang: targetLang,
});

while (true) {
  const { status } = await client.dubbing.getDubbingProjectMetadata(
    dubbed.dubbing_id
  );
  if (status === "dubbed") {
    const dubbedFile = await client.dubbing.getDubbedFile(
      dubbed.dubbing_id,
      targetLang
    );
    await play(dubbedFile);
    break;
  } else {
    console.log("Audio is still being dubbed...");
  }
  await new Promise((resolve) => setTimeout(resolve, 5000)); // Wait 5 seconds between checks
}

Execute the code with node example.mjs (or the equivalent command for Deno or Bun). In a few seconds, you should hear the audio play through your speaker.

Install the ElevenLabs SDK with npm

npm install elevenlabs

To play the audio through your speakers, you may be prompted to install MPV and/or ffmpeg.

With the ElevenLabs SDK installed, create a file called example.mjs and copy one of the following examples into it:

Convert text into life-like audio

import { ElevenLabsClient, play } from "elevenlabs";

const client = new ElevenLabsClient();
const audio = await client.textToSpeech.convert("JBFqnCBsd6RMkjVDRZzb", {
  text: "The first move is what sets everything in motion.",
  model_id: "eleven_multilingual_v2",
  output_format: "mp3_44100_128",
});

await play(audio);

Convert text into life-like audio

import { ElevenLabsClient, play } from "elevenlabs";

const client = new ElevenLabsClient();
const audio = await client.textToSpeech.convert("JBFqnCBsd6RMkjVDRZzb", {
  text: "The first move is what sets everything in motion.",
  model_id: "eleven_multilingual_v2",
  output_format: "mp3_44100_128",
});

await play(audio);

Transform audio from one voice to another

import { ElevenLabsClient, play } from "elevenlabs";
import fetch from "node-fetch";

const client = new ElevenLabsClient();
const voiceId = "JBFqnCBsd6RMkjVDRZzb";

const audioUrl = "https://storage.googleapis.com/eleven-public-cdn/audio/marketing/nicole.mp3";
const response = await fetch(audioUrl);
const audioBlob = new Blob([await response.arrayBuffer()], { type: "audio/mp3" });

const audioStream = await client.speechToSpeech.convert(voiceId, {
  audio: audioBlob,
  model_id: "eleven_multilingual_sts_v2",
  output_format: "mp3_44100_128",
});

await play(audioStream);

Convert text into sound effects

import { ElevenLabsClient, play } from "elevenlabs";

const client = new ElevenLabsClient();

const audio = await client.textToSoundEffects.convert({
  text: "Cinematic Braam, Horror",
});

await play(audio);

Removes background noise from audio.

import { ElevenLabsClient, play } from "elevenlabs";
import fetch from "node-fetch";

const client = new ElevenLabsClient();

const audioUrl =
  "https://storage.googleapis.com/eleven-public-cdn/audio/marketing/fin.mp3";
const response = await fetch(audioUrl);
const audioBlob = new Blob([await response.arrayBuffer()], {
  type: "audio/mp3",
});

const audioStream = await client.audioIsolation.audioIsolation({
  audio: audioBlob,
});

await play(audioStream);

Generate voices from a single text prompt.

import { ElevenLabsClient, play } from "elevenlabs";
import { Readable } from "stream";

const client = new ElevenLabsClient();

const voices = await client.textToVoice.createPreviews({
  voice_description: "A sassy squeaky mouse",
  text: "Every act of kindness, no matter how small, carries value and can make a difference, as no gesture of goodwill is ever wasted.",
});
const voicePreview1 = voices.previews[0].audio_base_64;

await play(Readable.from(Buffer.from(voicePreview1, "base64")));

Dub audio/video from one language to another

import { ElevenLabsClient, play } from "elevenlabs";
import fetch from "node-fetch";

const client = new ElevenLabsClient();

const targetLang = "es"; // spanish
const sourceAudio = await fetch(
  "https://storage.googleapis.com/eleven-public-cdn/audio/marketing/nicole.mp3"
);
const audioBlob = new Blob([await sourceAudio.arrayBuffer()], {
  type: "audio/mp3",
});

// Start dubbing
const dubbed = await client.dubbing.dubAVideoOrAnAudioFile({
  file: audioBlob,
  target_lang: targetLang,
});

while (true) {
  const { status } = await client.dubbing.getDubbingProjectMetadata(
    dubbed.dubbing_id
  );
  if (status === "dubbed") {
    const dubbedFile = await client.dubbing.getDubbedFile(
      dubbed.dubbing_id,
      targetLang
    );
    await play(dubbedFile);
    break;
  } else {
    console.log("Audio is still being dubbed...");
  }
  await new Promise((resolve) => setTimeout(resolve, 5000)); // Wait 5 seconds between checks
}

Execute the code with node example.mjs (or the equivalent command for Deno or Bun). In a few seconds, you should hear the audio play through your speaker.

To use the ElevenLabs API in Python, you can use the official ElevenLabs SDK for Python. Get started by installing the SDK using pip:

Install the ElevenLabs SDK with pip

pip install elevenlabs

To play the audio through your speakers, you may be prompted to install MPV and/or ffmpeg.

With the ElevenLabs SDK installed, create a file called example.py and copy one of the following examples into it:

Convert text into life-like audio

from elevenlabs.client import ElevenLabs
from elevenlabs import play

client = ElevenLabs()

audio = client.text_to_speech.convert(
    text="The first move is what sets everything in motion.",
    voice_id="JBFqnCBsd6RMkjVDRZzb",
    model_id="eleven_multilingual_v2",
    output_format="mp3_44100_128",
)

play(audio)

Convert text into life-like audio

from elevenlabs.client import ElevenLabs
from elevenlabs import play

client = ElevenLabs()

audio = client.text_to_speech.convert(
    text="The first move is what sets everything in motion.",
    voice_id="JBFqnCBsd6RMkjVDRZzb",
    model_id="eleven_multilingual_v2",
    output_format="mp3_44100_128",
)

play(audio)

Transform audio from one voice to another

from elevenlabs.client import ElevenLabs
from elevenlabs import play
import requests
from io import BytesIO

client = ElevenLabs()
voice_id = "JBFqnCBsd6RMkjVDRZzb"

audio_url = (
    "https://storage.googleapis.com/eleven-public-cdn/audio/marketing/nicole.mp3"
)
response = requests.get(audio_url)
audio_data = BytesIO(response.content)

audio_stream = client.speech_to_speech.convert(
    voice_id=voice_id,
    audio=audio_data,
    model_id="eleven_multilingual_sts_v2",
    output_format="mp3_44100_128",
)

play(audio_stream)

Convert text into sound effects

from elevenlabs.client import ElevenLabs
from elevenlabs import play

client = ElevenLabs()
audio = client.text_to_sound_effects.convert(text="Cinematic Braam, Horror")

play(audio)

Removes background noise from audio.

from elevenlabs.client import ElevenLabs
from elevenlabs import play
import requests
from io import BytesIO

client = ElevenLabs()

audio_url = "https://storage.googleapis.com/eleven-public-cdn/audio/marketing/fin.mp3"
response = requests.get(audio_url)
audio_data = BytesIO(response.content)

audio_stream = client.audio_isolation.audio_isolation(audio=audio_data)

play(audio_stream)

Generate voices from a single text prompt.

import base64
from elevenlabs.client import ElevenLabs
from elevenlabs import play

client = ElevenLabs()

voices = client.text_to_voice.create_previews(
    voice_description="A sassy squeaky mouse",
    text="Every act of kindness, no matter how small, carries value and can make a difference, as no gesture of goodwill is ever wasted.",
)

voice_preview = voices.previews[0].audio_base_64
audio_bytes = base64.b64decode(voice_preview)

play(audio_bytes)

Dub audio/video from one language to another

from elevenlabs.client import ElevenLabs
from elevenlabs import play
import requests
from io import BytesIO
import time

client = ElevenLabs()

target_lang = "es"  # Spanish

audio_url = (
    "https://storage.googleapis.com/eleven-public-cdn/audio/marketing/nicole.mp3"
)
response = requests.get(audio_url)

audio_data = BytesIO(response.content)
audio_data.name = "audio.mp3"

# Start dubbing
dubbed = client.dubbing.dub_a_video_or_an_audio_file(
    file=audio_data, target_lang=target_lang
)

while True:
    status = client.dubbing.get_dubbing_project_metadata(dubbed.dubbing_id).status
    if status == "dubbed":
        dubbed_file = client.dubbing.get_dubbed_file(dubbed.dubbing_id, target_lang)
        play(dubbed_file)
        break
    else:
        print("Audio is still being dubbed...")
        time.sleep(5)

Execute the code with python example.py. In a few seconds, you should hear the audio play through your speaker.

Get Started

Text to Speech

Text to Sound Effects

Dubbing

Create and export an API key

Make your first API request

Get Started

Text to Speech

Text to Sound Effects

Dubbing

​Create and export an API key

​Make your first API request

Create and export an API key

Make your first API request