Creates AudioNative enabled project, optionally starts conversion and returns project id and embeddable html snippet.

Whether to auto convert the project to audio or not.

Background color used in the player. If not provided, default background color set in the Player settings is used.

Either txt or HTML input file containing the article content. HTML should be formatted as follows '<html><body><div><p>Your content</p><h5>More of your content</h5><p>Some more of your content</p></div></body></html>'

Image URL used in the player. If not provided, default image set in the Player settings is used.

TTS Model ID used in the player. If not provided, default model ID set in the Player settings is used.

Specifies for how many minutes to persist the session across page reloads. If not provided, default sessionization set in the Player settings is used.

Whether to use small player or not. If not provided, default value set in the Player settings is used.

Text color used in the player. If not provided, default text color set in the Player settings is used.

Title used in the player and inserted at the top of the uploaded article. If not provided, the default title set in the Player settings is used.

Voice ID used to voice the content. If not provided, default voice ID set in the Player settings is used.

Dubs provided audio or video file into given language.

CSV file containing transcription/translation metadata

Whether to prepare dub for edits in dubbing studio.

A list of file paths to audio recordings intended for voice cloning

Whether to use the highest resolution available.

automatic or manual. Manual mode is only supported when creating a dubbing studio project

Number of speakers to use for the dubbing. Set to 0 to automatically detect the number of speakers

Start time of the source video/audio file.

The Target language to dub the content into. Can be none if dubbing studio editor is enabled and running manual mode

Whether to apply watermark to the output video.

Returns metadata about a dubbing project, including whether it’s still in progress or not

dubbing_id

Returns dubbed file as a streamed file. Videos will be returned in MP4 format and audio only dubs will be returned in MP3.

language_code

Returns metadata about all your generated audio.

How many history items to return at maximum

page_size

After which ID to start fetching, use this parameter to paginate across a large collection of history items. In case this parameter is not provided history items will be fetched starting from the most recently created one ordered descending by their creation date.

start_after_history_item_id

Voice ID to be filtered for, you can use GET https://api.elevenlabs.io/v1/voices to receive a list of voices and their IDs

voice_id

Returns information about an history item by its ID.

History item ID to be used, you can use GET https://api.elevenlabs.io/v1/history to receive a list of history items and their IDs.

history_item_id

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

A list of history items to download, you can get IDs of history items and other metadata using the GET https://api.elevenlabs.io/v1/history endpoint.

Output format to transcode the audio file, can be wav or default.

Returns a list of your projects together and its metadata.

Returns information about a specific project

The project_id of the project, you can query GET https://api.elevenlabs.io/v1/projects to list all available projects.

project_id

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

When the project is downloaded, should the returned audio have postprocessing in order to make it compliant with audiobook normalized volume requirements

A url that will be called by our service when the project is converted with a json containing the status of the conversion

The model_id of the model to be used for this project, you can query GET https://api.elevenlabs.io/v1/models to list all available models.

The voice_id that corresponds to the default voice used for new paragraph

The voice_id that corresponds to the default voice used for new titles

An optional .epub, .pdf, .txt or similar file can be provided. If provided, we will initialize the project with its content. If this is set, 'from_url' must be null. If neither 'from_url' or 'from_document' are provided we will initialize the project as blank.

An optional URL from which we will extract content to initialize the project. If this is set, 'from_url' must be null. If neither 'from_url' or 'from_document' are provided we will initialize the project as blank.

An optional ISBN number of the project you want to create, this will be added as metadata to the mp3 file on project / chapter download.

The name of the project, used for identification only.

A list of pronunciation dictionary locators (pronunciation_dictionary_id, version_id) encoded as a list of JSON strings for pronunciation dictionaries to be applied to the text. A list of json encoded strings is required as adding projects may occur through formData as opposed to jsonBody.

Output quality of the generated audio. Must be one of: standard - standard output format, 128kbps with 44.1kHz sample rate. high - high quality output format, 192kbps with 44.1kHz sample rate and major improvements on our side. Using this setting increases the character cost by 20%. ultra - ultra quality output format, 192kbps with 44.1kHz sample rate and highest improvements on our side. Using this setting increases the character cost by 50%. ultra lossless - ultra quality output format, 705.6kbps with 44.1kHz sample rate and highest improvements on our side in a fully lossless format. Using this setting increases the character cost by 100%.

An optional name of the author of the project, this will be added as metadata to the mp3 file on project / chapter download.

Starts conversion of a project and all of its chapters

Stream the audio from a project snapshot.

The project_snapshot_id of the project snapshot. You can query GET /v1/projects/{project_id}/snapshots to list all available snapshots for a project.

project_snapshot_id

Whether to convert the audio to mpeg format.

Returns a list of your chapters for a project together and its metadata

Returns information about a specific chapter.

The chapter_id of the chapter. You can query GET https://api.elevenlabs.io/v1/projects/{project_id}/chapters to list all available chapters for a project.

chapter_id

Gets information about all the snapshots of a chapter, each snapshot corresponds can be downloaded as audio. Whenever a chapter is converted a snapshot will be automatically created.

The chapter_snapshot_id of the chapter snapshot. You can query GET /v1/projects/{project_id}/chapters/{chapter_id}/snapshots to the all available snapshots for a chapter.

chapter_snapshot_id

Updates the set of pronunciation dictionaries acting on a project. This will automatically mark text within this project as requiring reconverting where the new dictionary would apply or the old one no longer does.

A list of pronunciation dictionary locators (pronunciation_dictionary_id, version_id) encoded as a list of JSON strings for pronunciation dictionaries to be applied to the text. A list of json encoded strings is required as adding projects may occur through formData as opposed to jsonBody

Creates a new pronunciation dictionary from a lexicon .PLS file

A description of the pronunciation dictionary, used for identification only.

A lexicon .pls file which we will use to initialize the project with.

The name of the pronunciation dictionary, used for identification only.

Should be one of 'editor' or 'viewer'. If not provided, defaults to no access.

Get a list of the pronunciation dictionaries you have access to and their metadata

Used for fetching next page. Cursor is returned in the response

cursor

How many pronunciation dictionaries to return at maximum. Can not exceed 100, defaults to 30.

Get metadata for a pronunciation dictionary

pronunciation_dictionary_id

Add rules to the pronunciation dictionary

List of pronunciation rules. Rule can be either: an alias rule: {'string_to_replace': 'a', 'type': 'alias', 'alias': 'b', } or a phoneme rule: {'string_to_replace': 'a', 'type': 'phoneme', 'phoneme': 'b', 'alphabet': 'ipa' }

Remove rules from the pronunciation dictionary

List of strings to remove from the pronunciation dictionary.

Get PLS file with a pronunciation dictionary version rules

dictionary_id

The id of the version of the pronunciation dictionary

version_id

Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.

Sample ID to be used, you can use GET https://api.elevenlabs.io/v1/voices/{voice_id} to list all the available samples for a voice.

sample_id

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

Create sound effects for your videos, voice-overs or video games.

The duration of the sound which will be generated in seconds. Must be at least 0.5 and at most 22. If set to None we will guess the optimal duration using the prompt. Defaults to None.

A higher prompt influence makes your generation follow the prompt more closely while also making generations less variable. Must be a value between 0 and 1. Defaults to 0.3.

The text that will get converted into a sound effect.

Use Speech to Speech API to transform uploaded speech so it sounds like it was spoken by another voice

When enable_logging is set to false full privacy mode will be used for the request. This will mean history features are unavailable for this request, including request stitching. Full privacy mode may only be used by enterprise customers.

enable_logging

You can turn on latency optimizations at some cost of quality. The best possible final latency varies by model

optimize_streaming_latency

Output format of the generated audio. Must be one of: mp3_22050_32 - output format, mp3 with 22.05kHz sample rate at 32kbps. mp3_44100_32 - output format, mp3 with 44.1kHz sample rate at 32kbps. mp3_44100_64 - output format, mp3 with 44.1kHz sample rate at 64kbps. mp3_44100_96 - output format, mp3 with 44.1kHz sample rate at 96kbps. mp3_44100_128 - default output format, mp3 with 44.1kHz sample rate at 128kbps. mp3_44100_192 - output format, mp3 with 44.1kHz sample rate at 192kbps. Requires you to be subscribed to Creator tier or above. pcm_16000 - PCM format (S16LE) with 16kHz sample rate. pcm_22050 - PCM format (S16LE) with 22.05kHz sample rate. pcm_24000 - PCM format (S16LE) with 24kHz sample rate. pcm_44100 - PCM format (S16LE) with 44.1kHz sample rate. Requires you to be subscribed to Pro tier or above. ulaw_8000 - μ-law format (sometimes written mu-law, often approximated as u-law) with 8kHz sample rate. Note that this format is commonly used for Twilio audio inputs.

output_format

The audio file which holds the content and emotion that will control the generated speech.

Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for speech to speech, you can check this using the can_do_voice_conversion property.

If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed.

Voice settings overriding stored setttings for the given voice. They are applied only on the given request. Needs to be send as a JSON encoded string.

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

API that converts text into lifelike speech with best-in-class latency & uses the most advanced AI audio model ever.

Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property

A list of request_id of the samples that were generated before this generation. Can be used to improve the flow of prosody when splitting up a large task into multiple requests. The results will be best when the same model is used across the generations. In case both next_text and next_request_ids is send, next_text will be ignored. A maximum of 3 request_ids can be send.

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

A list of request_id of the samples that were generated before this generation. Can be used to improve the flow of prosody when splitting up a large task into multiple requests. The results will be best when the same model is used across the generations. In case both previous_text and previous_request_ids is send, previous_text will be ignored. A maximum of 3 request_ids can be send.

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

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

The text that will get converted into speech

Voice settings overriding stored setttings for the given voice. They are applied only on the given reques

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

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

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

Gets extended information about the users subscription

Generate a random voice based on parameters

Category code corresponding to the accent of the generated voice. Possible values: american, british, african, australian, indian

The strength of the accent of the generated voice. Has to be between 0.3 and 2.0.

Category code corresponding to the age of the generated voice. Possible values: young, middle_aged, old.

Category code corresponding to the gender of the generated voice. Possible values: female, male.

Text to generate, text length has to be between 100 and 1000.

How many shared voices to return at maximum. Can not exceed 100, defaults to 30.

gender

accent

language

search

use_cases

descriptives

featured

Filter voices that are enabled for the reader app

reader_app_enabled

owner_id

sort

page

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

Public user ID used to publicly identify ElevenLabs users.

public_user_id

The name that identifies this voice. This will be displayed in the dropdown of the website.

Gets a list of all available voices for a user.

Returns the settings for a specific voice.

If set will return settings information corresponding to the voice, requires authorization

with_settings

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

Serialized labels dictionary for the voice.

Sends an email invitation to join your workspace to the provided email

Invalidates an existing email invitation. The invitation will still show up in the inbox it has been delivered to, but activating it to join the workspace won’t work. This endpoint may only be called by workspace administrators.

Updates attributes of a workspace member.

Whether to lock or unlock the user account.

Role dictating permissions in the workspace.

ElevenLabs

Pre-configured, Predictable, Single Interface, Ready-to-use, Opinionated & Managed API Explorer & Server - LowCodeAPI

Pre-configured, Predictable, Single Interface, Ready-to-use, Opinionated & Managed API Explorer & Server. Bring your API credentials, configure and access your 3rd party APIs. Using LowCodeAPI securely manage all integrations in one place.

LowCodeAPI

Build Your Own 

Build & Bundle Your Own Custom API integrations and run independently.

API Token

Generate API Token

OpenAI

Google Sheets

Google Docs

Notion

Gmail

Unsplash

Google Drive

Google Forms

Name.com

Gumroad

Trello

Telegram

The Stripe API is organized around REST. Our API has predictable resource-oriented URLs, accepts form-encoded request bodies, returns JSON-encoded responses, and uses standard HTTP response codes, authentication, and verbs.