Elevenlabs | Text to Audio

fal-ai/elevenlabs/tts/eleven-v3

Generate text-to-speech audio using Eleven-v3 from ElevenLabs.

Inference

Commercial use

Streaming

Partner

Schema

LLMs

Playground API

About

Eleven V3

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Migrate to @fal-ai/client

The @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Please check the migration guide for more information.

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/elevenlabs/tts/eleven-v3", {
  input: {
    text: "Hello! This is a test of the text to speech system, powered by ElevenLabs. How does it sound?"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

Streaming#

This model supports streaming requests. You can stream data directly to the model and get the result in real-time.

import { fal } from "@fal-ai/client";

const stream = await fal.stream("fal-ai/elevenlabs/tts/eleven-v3", {
  input: {
    text: "Hello! This is a test of the text to speech system, powered by ElevenLabs. How does it sound?"
  }
});

for await (const event of stream) {
  console.log(event);
}

const result = await stream.done();

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration.

import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

Protect your API Key

When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.

3. Queue#

Long-running requests

For long-running requests, such as training jobs or models with slower inference times, it is recommended to check the Queue status and rely on Webhooks instead of blocking while waiting for the result.

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("fal-ai/elevenlabs/tts/eleven-v3", {
  input: {
    text: "Hello! This is a test of the text to speech system, powered by ElevenLabs. How does it sound?"
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("fal-ai/elevenlabs/tts/eleven-v3", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("fal-ai/elevenlabs/tts/eleven-v3", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Auto uploads

The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).

Read more about file handling in our file upload guide.

5. Schema#

Input#

text string* required

The text to convert to speech

voice string

The voice to use for speech generation Default value: "Rachel"

stability float

Voice stability (0-1) Default value: 0.5

similarity_boost float

Similarity boost (0-1) Default value: 0.75

style float

Style exaggeration (0-1)

speed float

Speech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality. Default value: 1

timestamps boolean

Whether to return timestamps for each word in the generated speech

previous_text string

The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.

next_text string

The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.

language_code string

Language code (ISO 639-1) used to enforce a language for the model. Currently only Turbo v2.5 and Flash v2.5 support language enforcement. For other models, an error will be returned if language code is provided.

{
  "text": "Hello! This is a test of the text to speech system, powered by ElevenLabs. How does it sound?",
  "voice": "Aria",
  "stability": 0.5,
  "similarity_boost": 0.75,
  "speed": 1
}

Output#

audio File* required

The generated audio file

timestamps list<void>

Timestamps for each word in the generated speech. Only returned if timestamps is set to True in the request.

{
  "audio": {
    "url": "https://v3.fal.media/files/zebra/zJL_oRY8h5RWwjoK1w7tx_output.mp3"
  }
}

Other types#

SpeechToTextRequest#

audio_url string* required

URL of the audio file to transcribe

language_code string

Language code of the audio

tag_audio_events boolean

Tag audio events like laughter, applause, etc. Default value: true

diarize boolean

Whether to annotate who is speaking Default value: true

TextToSpeechStreamRequest#

text string* required

The text to convert to speech

voice string

The voice to use for speech generation Default value: "Rachel"

stability float

Voice stability (0-1) Default value: 0.5

similarity_boost float

Similarity boost (0-1) Default value: 0.75

style float

Style exaggeration (0-1)

speed float

Speech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality. Default value: 1

TextToVoiceDesignRequest#

prompt string* required

Description to use for the created voice.

text string

The text that will be voiced by the created voice. If not provided auto_generate_text must be enabled.

auto_generate_text boolean

Whether to automatically generate a text suitable for the voice description. If text is provided, this field must be disabled. Default value: true

loudness float

Controls the volume level of the generated voice. -1 is quietest, 1 is loudest, 0 corresponds to roughly -24 LUFS. Default value: 0.5

seed integer

Random number that controls the voice generation. Same seed with same inputs produces same voice.

guidance_scale float

Controls how closely the AI follows the prompt. Lower numbers give the AI more freedom to be creative, while higher numbers force it to stick more to the prompt. High numbers can cause voice to sound artificial or robotic. We recommend to use longer, more detailed prompts at lower Guidance Scale. Default value: 5

audio_url string

Reference audio to use for the voice generation.

prompt_strength float

Controls the balance of prompt versus reference audio when generating voice samples. 0 means almost no prompt influence, 1 means almost no reference audio influence. Only supported when providing reference audio.

output_format OutputFormatEnum

Output format of the generated audio. Formatted as codec_sample_rate_bitrate. Default value: "mp3_44100_128"

Possible enum values: mp3_22050_32, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, pcm_8000, pcm_16000, pcm_22050, pcm_24000, pcm_44100, pcm_48000, ulaw_8000, alaw_8000, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192

remixing_session_id string

The remixing session id.

remixing_session_iteration_id string

The id of the remixing session iteration where these generations should be attached to. If not provided, a new iteration will be created.

sync_mode boolean

If True, the media will be returned as a data URI and the output data won't be available in the request history.

TextToVoiceRemixRequest#

prompt string* required

Description to use for the created voice.

text string

The text that will be voiced by the created voice. If not provided auto_generate_text must be enabled.

auto_generate_text boolean

Whether to automatically generate a text suitable for the voice description. If text is provided, this field must be disabled. Default value: true

loudness float

Controls the volume level of the generated voice. -1 is quietest, 1 is loudest, 0 corresponds to roughly -24 LUFS. Default value: 0.5

seed integer

Random number that controls the voice generation. Same seed with same inputs produces same voice.

guidance_scale float

prompt_strength float

output_format OutputFormatEnum

Output format of the generated audio. Formatted as codec_sample_rate_bitrate. Default value: "mp3_44100_128"

remixing_session_id string

The remixing session id.

remixing_session_iteration_id string

The id of the remixing session iteration where these generations should be attached to. If not provided, a new iteration will be created.

sync_mode boolean

If True, the media will be returned as a data URI and the output data won't be available in the request history.

voice string* required

The name or the ID (voice_id) of the voice to be used for the remix.

AudioIsolationRequest#

audio_url string* required

URL of the audio file to isolate voice from

File#

url string* required

The URL where the file can be downloaded from.

content_type string

The mime type of the file.

file_name string

The name of the file. It will be auto-generated if not provided.

file_size integer

The size of the file in bytes.

TextToDialogueRequest#

inputs list<DialogueBlock>* required

A list of dialogue inputs, each containing text and a voice ID which will be converted into speech.

stability float

Determines how stable the voice is and the randomness between each generation. Lower values introduce broader emotional range for the voice. Higher values can result in a monotonous voice with limited emotion.

use_speaker_boost boolean

This setting boosts the similarity to the original speaker. Using this setting requires a slightly higher computational load, which in turn increases latency.

pronunciation_dictionary_locators list<PronunciationDictionaryLocator>

A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request

seed integer

Random seed for reproducibility.

PronunciationDictionaryLocator#

pronunciation_dictionary_id string* required

The ID of the pronunciation dictionary.

version_id string

The ID of the version of the pronunciation dictionary. If not provided, the latest version will be used.

VoiceChangerRequest#

voice string

The voice to use for speech generation Default value: "Rachel"

audio_url string* required

The input audio file

VoiceCloningRequest#

audio_urls list<AudioInput>* required

List of audio files to use for voice cloning

remove_background_noise boolean

Whether to remove background noise from the audio files Default value: true

VoicePreview#

audio File* required

The generated voice

generated_voice_id string* required

The ID of the generated voice

media_type string* required

The media type of the generated audio

duration_seconds float* required

Duration of the generated audio in seconds

language string* required

The language of the preview

SoundEffectRequest#

text string* required

The text describing the sound effect to generate

duration_seconds float

Duration in seconds (0.5-22). If None, optimal duration will be determined from prompt.

prompt_influence float

How closely to follow the prompt (0-1). Higher values mean less variation. Default value: 0.3

output_format OutputFormatEnum

Output format of the generated audio. Formatted as codec_sample_rate_bitrate. Default value: "mp3_44100_128"

TextToVoiceCreateRequest#

voice_name string* required

Name to use for the created voice.

voice_description string* required

Description to use for the created voice.

generated_voice_id string* required

The generated_voice_id to create, call /text-to-voice/design/eleven-v3 and fetch the generated_voice_id from the response if don't have one yet.

labels object

Optional, metadata to add to the created voice. Defaults to None.

played_not_selected_voice_ids list<string>

Optional, list of voice IDs that were played but not selected by the user during the voice creation process. Defaults to None.

DialogueBlock#

text string* required

The dialogue text

voice string* required

The name or the ID of the voice to be used for the generation.

SoundEffectRequestV2#

text string* required

The text describing the sound effect to generate

duration_seconds float

Duration in seconds (0.5-22). If None, optimal duration will be determined from prompt.

prompt_influence float

How closely to follow the prompt (0-1). Higher values mean less variation. Default value: 0.3

output_format OutputFormatEnum

Output format of the generated audio. Formatted as codec_sample_rate_bitrate. Default value: "mp3_44100_128"

loop boolean

Whether to create a sound effect that loops smoothly.

TranscriptionWord#

text string* required

The transcribed word or audio event

start float* required

Start time in seconds

end float* required

End time in seconds

type string* required

Type of element (word, spacing, or audio_event)

speaker_id string

Speaker identifier if diarization was enabled

Elevenlabs Text to Audio

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

Streaming#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

SpeechToTextRequest#

TextToSpeechStreamRequest#

TextToVoiceDesignRequest#

TextToVoiceRemixRequest#

AudioIsolationRequest#

File#

TextToDialogueRequest#

PronunciationDictionaryLocator#

VoiceChangerRequest#

VoiceCloningRequest#

VoicePreview#

SoundEffectRequest#

TextToVoiceCreateRequest#

DialogueBlock#

SoundEffectRequestV2#

TranscriptionWord#