Elevenlabs
Learn how to use Elevenlabs with Composio
Overview
Enum
ELEVENLABS
Description
Create natural AI voices instantly in any language - perfect for video creators, developers, and businesses.
Authentication Details
API_KEY
Actions
ELEVENLABS_GET_USER_SUBSCRIPTION_INFO
Retrieves the current user’s subscription information from the elevenlabs platform. this endpoint provides details about the user’s subscription status, tier, and associated limits or features. it should be used when an application needs to check the capabilities and restrictions of the authenticated user’s account. the endpoint does not require any additional parameters, as it uses the authenticated user’s context to fetch the relevant subscription data. note that this endpoint will not provide information about other users’ subscriptions or historical subscription data.
Action Parameters
Action Response
ELEVENLABS_GET_AUDIO_FROM_HISTORY_ITEM
Retrieves the audio file associated with a specific history item in the elevenlabs text-to-speech platform. this endpoint allows users to access previously generated audio content by providing the unique identifier of the history item. it returns the audio data in mpeg format, which can be played or further processed as needed. use this endpoint when you need to fetch the audio output of a past text-to-speech conversion or when you want to replay or download a specific audio item from your history.
Action Parameters
Action Response
ELEVENLABS_GET_TRANSCRIPT_FOR_DUB
Retrieves the transcript for a specific dubbing project in the requested language. this endpoint is used to fetch the textual content that has been prepared for dubbing in a particular language. it’s essential for reviewing or processing the transcript before or after the actual voice generation process. the endpoint should be used when working with multilingual dubbing projects or when needing to access the textual content of a dubbing job in a specific language. it does not provide the audio file of the dubbed content, only the transcript. the availability and content of the transcript may depend on the current state of the dubbing project and the supported languages.
Action Parameters
Action Response
ELEVENLABS_GET_CHAPTERS
Retrieves a list of chapters associated with a specific project in the elevenlabs platform. this endpoint is useful for developers who need to fetch the structure or content organization of a text-to-speech project. it can be used to get an overview of the chapters within a project, which may represent different sections or segments of the audio content. the endpoint is particularly helpful when managing large-scale audio projects or when implementing features that require chapter-based navigation or playback. note that this endpoint only provides chapter information and does not include the actual audio content.
Action Parameters
Action Response
ELEVENLABS_GET_MODELS
Retrieves a list of available text-to-speech models from the elevenlabs platform. this endpoint provides developers with information about the current models that can be used for voice synthesis. it should be used when initializing an application or when a user needs to choose a specific model for their text-to-speech tasks. the endpoint does not require any parameters, making it straightforward to query for up-to-date model information. however, it’s important to note that this endpoint only provides model details and does not perform any actual text-to-speech conversion.
Action Parameters
Action Response
ELEVENLABS_DELETE_CHAPTER
Deletes a specific chapter from a project within the elevenlabs platform. this endpoint is used to remove unwanted or obsolete chapters from a project, helping to manage and organize text-to-speech content. it should be used when a user needs to permanently remove a chapter and its associated data from a project. note that this action is irreversible, and once a chapter is deleted, it cannot be recovered. ensure that the correct project id and chapter id are provided to avoid unintended deletions.
Action Parameters
Action Response
ELEVENLABS_DELETE_DUBBING_PROJECT
Deletes a specific dubbing asset from the elevenlabs platform. this endpoint should be used when you need to permanently remove a dubbing project or its associated audio files from your account. it’s important to note that this action is irreversible, and once a dubbing asset is deleted, it cannot be recovered. use this endpoint with caution, ensuring that the dubbing asset is no longer needed before deletion. this operation helps manage storage and organize your dubbing projects by removing unnecessary or outdated content.
Action Parameters
Action Response
ELEVENLABS_TEXT_TO_SPEECH
Converts text into speech using a voice of your choice and returns audio.
Action Parameters
Action Response
ELEVENLABS_ADD_SHARING_VOICE
Adds a shared voice to a user’s account in the elevenlabs text-to-speech platform. this endpoint allows users to incorporate voices shared by other users into their own voice library. it requires specifying the public user id of the account adding the voice, the unique identifier of the voice being added, and a new name for the voice in the user’s account. this endpoint is useful for expanding a user’s voice options and collaborating with other users on the platform. note that this endpoint only adds an existing shared voice and does not create a new voice or modify the original shared voice.
Action Parameters
Action Response
ELEVENLABS_CREATE_A_PREVIOUSLY_GENERATED_VOICE
This endpoint finalizes the creation of a previously generated voice in the elevenlabs text-to-speech platform. it allows you to assign a name, description, and optional metadata to a voice that has already been generated using the voice generation process. use this endpoint when you have successfully generated a voice using the post /v1/voice-generation/generate-voice endpoint and want to complete its setup for use in text-to-speech operations. this step is crucial for organizing and managing your custom voices within the elevenlabs ecosystem. note that you must have a valid generated voice id from a previous generation process to use this endpoint successfully.
Action Parameters
Action Response
ELEVENLABS_GET_DUBBING_PROJECT_METADATA
Retrieves the current status of a specific dubbing job in the elevenlabs platform. this endpoint should be used to check the progress or completion of a previously initiated dubbing task. it provides information about whether the dubbing is in progress, completed, or encountered any errors. the endpoint is particularly useful for monitoring long-running dubbing jobs or implementing status checks in applications that use elevenlabs’ dubbing features. note that this endpoint does not initiate new dubbing jobs or modify existing ones; it’s purely for status retrieval.
Action Parameters
Action Response
ELEVENLABS_SPEECH_TO_SPEECH
Converts an input audio file to speech using a specified voice and ai model, allowing for customized voice settings and optional deterministic sampling. this endpoint enables the transformation of audio content while preserving emotional nuances, making it ideal for voice cloning, accent modification, or creating personalized voiceovers. it should be used when you need to generate speech that mimics the style and emotion of a given audio input. the endpoint requires multipart/form-data content type and supports various ai models for different languages and use cases.
Action Parameters
Action Response
ELEVENLABS_EDIT_VOICE_SETTINGS
Edits the voice settings for a specific voice id in the elevenlabs text-to-speech platform. this endpoint allows fine-tuning of various aspects of voice generation, including stability, similarity to the original voice, style emphasis, and speaker boost. use this endpoint when you need to customize the voice output for specific use cases or to achieve desired voice characteristics. the changes made through this endpoint will affect future voice generations using the specified voice id. note that adjusting these settings may impact the quality, consistency, and performance of the generated voice, so careful tuning and testing are recommended.
Action Parameters
Action Response
ELEVENLABS_DELETE_SAMPLE
Deletes a specific voice sample associated with a particular voice in the elevenlabs text-to-speech system. this endpoint should be used when you need to remove a previously added custom voice sample from a voice. it’s particularly useful for managing voice libraries, cleaning up unused samples, or complying with data retention policies. note that this operation is irreversible, and once a sample is deleted, it cannot be recovered. use this endpoint with caution as it permanently removes data from the system.
Action Parameters
Action Response
ELEVENLABS_GET_DEFAULT_VOICE_SETTINGS
Retrieves the default voice settings for the elevenlabs text-to-speech service. this endpoint provides the baseline configuration used for voice generation when no custom settings are specified. it’s useful for understanding the starting point of voice parameters and can be called before making adjustments for specific use cases. the returned settings likely include defaults for voice stability, similarity boost, and other relevant voice generation parameters. this endpoint doesn’t modify any settings and is safe to call at any time to reference the default configuration.
Action Parameters
Action Response
ELEVENLABS_GET_DUBBED_FILE
Retrieves the audio file for a specific dubbing project in a particular language. this endpoint is used to fetch the dubbed audio content that has been generated or processed by elevenlabs for a given dubbing task. it should be used when you need to access the audio output of a dubbing project, such as for playback, download, or further processing. the endpoint requires both the dubbing project identifier and the desired language code to locate and return the correct audio file. it’s important to note that this endpoint only provides access to existing dubbed audio and does not initiate new dubbing tasks or modify existing ones.
Action Parameters
Action Response
ELEVENLABS_GET_PROJECT_SNAPSHOTS
Retrieves a list of snapshots for a specific project in elevenlabs. this endpoint allows you to access saved states or versions of a project, including information about the current state and associated audio files. use this endpoint when you need to track project history, compare different versions, or retrieve specific states of a project for further processing or playback. it’s particularly useful for managing and accessing multiple iterations of text-to-speech projects.
Action Parameters
Action Response
ELEVENLABS_ADD_A_PRONUNCIATION_DICTIONARY
This endpoint allows users to add a new pronunciation dictionary to the elevenlabs text-to-speech system by uploading a lexicon file. it is primarily used to improve pronunciation accuracy for specific words, technical terms, or domain-specific vocabulary in speech synthesis. the endpoint accepts a .pls file containing pronunciation rules, along with metadata such as name, description, and access control settings. this function is essential for customizing and fine-tuning the text-to-speech output for specialized use cases or languages.
Action Parameters
Action Response
ELEVENLABS_CONVERT_CHAPTER
Converts a specific chapter within a project to audio format using elevenlabs’ text-to-speech technology. this endpoint is used to transform the textual content of a chapter into high-quality, natural-sounding speech. it’s particularly useful for creating audiobooks, podcast episodes, or any other audio content from written material. the conversion process applies the advanced text-to-speech algorithms of elevenlabs, potentially allowing for customization of voice characteristics and speech patterns. users should ensure that the project and chapter ids are correct before making the request, as incorrect ids will result in failed conversions.
Action Parameters
Action Response
ELEVENLABS_ADD_RULES_TO_THE_PRONUNCIATION_DICTIONARY
This endpoint adds pronunciation rules to a specific pronunciation dictionary in the elevenlabs text-to-speech platform. it allows users to define custom pronunciations for words or phrases, enhancing the accuracy and naturalness of speech synthesis. the endpoint supports two types of rules: alias rules for simple string replacements, and phoneme rules for specifying exact pronunciations using phonetic alphabets like ipa or cmu. this functionality is particularly useful for handling proper nouns, acronyms, or words with non-standard pronunciations. use this endpoint when you need to fine-tune the pronunciation of specific words in your text-to-speech applications.
Action Parameters
Action Response
ELEVENLABS_STREAM_CHAPTER_AUDIO
Streams the audio content of a specific chapter snapshot from a project. this endpoint allows you to retrieve and play the audio associated with a particular version (snapshot) of a chapter within your elevenlabs project. it’s particularly useful for applications that need to access and stream chapter audio, such as audiobook players, language learning apps, or any system that manages audio content in a project-based structure. the endpoint supports optional mpeg conversion, making it versatile for various audio playback scenarios. use this when you need to retrieve and stream the latest version of a chapter’s audio or when you want to access a specific historical version of the audio content.
Action Parameters
Action Response
ELEVENLABS_DOWNLOAD_HISTORY_ITEMS
Allows users to download multiple previously synthesized audio clips from their elevenlabs history. this endpoint is useful for retrieving a batch of audio files at once, saving time compared to downloading them individually. it should be used when you need to access multiple historical audio items, such as for backup purposes or offline processing. the endpoint requires a list of history item ids and optionally allows specifying the output format. note that this endpoint does not provide any additional metadata about the audio files; it’s purely for downloading the audio content.
Action Parameters
Action Response
ELEVENLABS_EDIT_VOICE
The editvoice endpoint allows you to modify an existing voice model in the elevenlabs text-to-speech platform. this tool is used to update various properties of a specific voice, identified by its voice id. it supports changing the voice’s name, adding new audio files to refine the voice model, updating the voice’s description, and modifying associated labels. this endpoint is particularly useful for fine-tuning and maintaining voice models over time, ensuring they remain up-to-date and accurately described within the elevenlabs ecosystem.
Action Parameters
Action Response
ELEVENLABS_GENERATE_A_RANDOM_VOICE
Generates a random voice with specified characteristics using elevenlabs’ advanced text-to-speech synthesis platform. this endpoint allows users to create custom voice outputs by defining gender, accent, age, and accent strength, along with the text to be spoken. it’s ideal for creating diverse voice samples, prototyping voice-based applications, or generating unique audio content. the endpoint provides flexibility in voice customization while ensuring high-quality, natural-sounding speech output.
Action Parameters
Action Response
ELEVENLABS_SPEECH_TO_SPEECH_STREAMING
The speech to speech streaming endpoint converts input audio to synthesized speech using a specified voice and model, with real-time streaming capabilities. it allows for the transformation of speech content and emotion from the input audio into a new voice, enabling applications like voice cloning, accent modification, or expressive speech synthesis. this endpoint should be used when you need to perform speech-to-speech conversion with immediate audio output, ideal for real-time applications or processing large audio files without waiting for the entire conversion to complete. note that the quality and accuracy of the conversion depend on the clarity of the input audio and the chosen model’s capabilities.
Action Parameters
Action Response
ELEVENLABS_GET_HISTORY_ITEM_BY_ID
Retrieves a specific history item from the elevenlabs text-to-speech platform. this endpoint allows users to fetch detailed information about a previously generated audio item using its unique identifier. it is particularly useful for accessing metadata, such as the original text, voice settings used, and generation date of a specific audio generation request. this tool should be used when you need to retrieve information about a particular text-to-speech conversion from the user’s history, but it will not provide the actual audio file. for downloading the audio file, a separate endpoint would likely be required.
Action Parameters
Action Response
ELEVENLABS_GET_A_PROFILE_PAGE
Retrieves the public profile information for a specific elevenlabs user based on their unique handle. this endpoint allows developers to access publicly available data about a user, which may include their username, bio, voice samples, or other shareable information. it’s particularly useful for applications that need to display user profiles or verify a user’s existence on the platform. the endpoint should be used when you need to fetch up-to-date profile data for a known user handle. however, it will not provide access to private user information or data that the user has chosen not to make public.
Action Parameters
Action Response
ELEVENLABS_STREAMS_ARCHIVE_WITH_PROJECT_AUDIO
Archives a specific snapshot of a project in the elevenlabs platform. this endpoint is used when you want to create a permanent, immutable copy of a project’s state at a particular point in time. archiving a snapshot can be useful for version control, backup purposes, or to preserve a specific configuration of your text-to-speech project. once archived, the snapshot is likely read-only and cannot be modified, ensuring the integrity of the archived state. this operation is typically irreversible, so it should be used with caution and only when you’re certain you want to create a permanent archive of the project snapshot.
Action Parameters
Action Response
ELEVENLABS_GET_GENERATED_ITEMS
The gethistoryendpoint retrieves historical data related to your elevenlabs api usage. this endpoint allows you to access logs of past text-to-speech conversions, including details such as the text input, voice used, and generation timestamps. it’s particularly useful for tracking your api usage, auditing past requests, or recovering previously generated audio content. the endpoint doesn’t modify any data and is intended for read-only operations. while it provides valuable insights into your account’s activity, it may not include the actual audio files and might have limitations on how far back the history goes.
Action Parameters
Action Response
ELEVENLABS_GET_VOICE
Retrieves detailed information about a specific voice model from the elevenlabs text-to-speech platform. this endpoint is used to fetch comprehensive data about a particular voice, including its characteristics, settings, and any associated metadata. it’s essential for developers who need to inspect or verify the properties of a voice before using it in text-to-speech conversions. the endpoint requires a valid voice id and returns a detailed profile of the requested voice, which can be useful for voice selection, customization, or troubleshooting in tts applications.
Action Parameters
Action Response
ELEVENLABS_GET_PROJECTS
Retrieves a list of all projects associated with the user’s elevenlabs account. this endpoint allows developers to access and manage their text-to-speech and voice synthesis projects. it should be used when you need to view, organize, or select specific projects for further operations. the response likely includes project details such as id, name, creation date, and associated voices. note that this endpoint does not create, modify, or delete projects; it only provides a read-only view of existing projects.
Action Parameters
Action Response
ELEVENLABS_GET_AUDIO_FROM_SAMPLE
Retrieves the audio content of a specific sample associated with a particular voice in the elevenlabs text-to-speech platform. this endpoint allows developers to access and play back individual voice samples, which can be useful for voice quality assessment, demonstration purposes, or further processing. the endpoint requires both a voice id and a sample id to precisely locate and return the desired audio content. it should be used when there’s a need to listen to or analyze a specific voice sample without generating new audio from text.
Action Parameters
Action Response
ELEVENLABS_DUB_A_VIDEO_OR_AN_AUDIOFILE_V_1_DUBBING_POST
This endpoint allows you to dub a video or audio file into a target language using elevenlabs’ advanced text-to-speech synthesis. it supports both automatic and manual dubbing modes, with options for voice cloning, speaker detection, and studio editing. the tool is ideal for content creators, filmmakers, and developers looking to localize audio content or create multilingual versions of their media. it offers flexibility in input methods, including direct file upload or url-based source retrieval, and provides control over dubbing parameters such as language selection, speaker count, and output quality. the endpoint can handle complex dubbing scenarios, including separate foreground and background audio processing when used with csv metadata input.(DEPRECATED use dub_a_video_or_an_audio_file)
Action Parameters
Action Response
ELEVENLABS_CONVERT_PROJECT
Converts text to speech within a specified project using elevenlabs’ advanced text-to-speech synthesis. this endpoint allows developers to generate high-quality, natural-sounding voice audio from provided text, leveraging project-specific settings and voices. it’s ideal for creating dynamic audio content, voice-overs, or integrating speech capabilities into applications. the conversion process takes into account project-specific configurations, ensuring consistency and customization options for the generated speech.
Action Parameters
Action Response
ELEVENLABS_ADD_VOICE
The ‘add voice’ endpoint allows users to add a new voice to the elevenlabs platform for voice cloning and synthesis. it initiates the voice cloning process by uploading audio samples and providing necessary metadata. this endpoint should be used when creating a new custom voice for text-to-speech applications. it’s particularly useful for developers looking to expand their voice options or create personalized voice experiences. the endpoint requires at least one audio file for voice cloning, but multiple files can be provided for better results. note that the actual voice cloning process may take some time after the successful api call, and the voice may not be immediately available for use.
Action Parameters
Action Response
ELEVENLABS_GET_METADATA_FOR_A_PRONUNCIATION_DICTIONARY
Retrieves a specific pronunciation dictionary by its unique identifier from the elevenlabs text-to-speech platform. this endpoint allows developers to access the details and content of a particular pronunciation dictionary, which can be used to improve the accuracy and naturalness of speech synthesis for specific words or phrases. it’s particularly useful when you need to review or apply custom pronunciation rules in your text-to-speech applications. the endpoint returns the complete information about the requested dictionary, including its name, language, and pronunciation entries. use this when you need to inspect or verify the contents of a pronunciation dictionary before applying it to your text-to-speech requests.
Action Parameters
Action Response
ELEVENLABS_GET_USER_INFO
Retrieves detailed information about the currently authenticated user’s account. this endpoint provides access to the user’s profile data, which may include account settings, subscription details, usage statistics, and other relevant information. it should be used when you need to fetch up-to-date user-specific data, such as remaining character quota or subscription status. the endpoint does not accept any parameters, as it operates based on the authenticated user’s context. note that this endpoint likely requires a valid api key for authentication, and usage may be subject to rate limiting based on the user’s subscription tier.
Action Parameters
Action Response
ELEVENLABS_GET_CHAPTER_SNAPSHOTS
Retrieves snapshots for a specific chapter within a project in the elevenlabs platform. this endpoint allows users to access different versions or states of a chapter, which can be useful for tracking changes, reverting to previous versions, or comparing different iterations of voice synthesis work. it should be used when there’s a need to review or manage the history of a particular chapter in a text-to-speech project. the endpoint requires both a project id and a chapter id to pinpoint the exact resource for which snapshots are requested. it’s important to note that the availability and number of snapshots may depend on the project’s settings and the user’s subscription tier.
Action Parameters
Action Response
ELEVENLABS_ADD_PROJECT
Creates a new text-to-speech project in the elevenlabs platform with customizable voice and content settings. this endpoint allows for initializing a project from a url or uploaded document, setting default voices for titles and paragraphs, specifying audio quality, and applying pronunciation dictionaries. it’s particularly useful for creating audiobooks, podcasts, or other long-form audio content with consistent voice and pronunciation settings. the project can be initialized with content or left blank for later population.
Action Parameters
Action Response
ELEVENLABS_GET_USER_INFO_V_1_USER_GET
Retrieves detailed information about the currently authenticated user’s account. this endpoint provides access to the user’s profile data, which may include account settings, subscription details, usage statistics, and other relevant information. it should be used when you need to fetch up-to-date user-specific data, such as remaining character quota or subscription status. the endpoint does not accept any parameters, as it operates based on the authenticated user’s context. note that this endpoint likely requires a valid api key for authentication, and usage may be subject to rate limiting based on the user’s subscription tier.(DEPRECATED use get_user_info)
Action Parameters
Action Response
ELEVENLABS_GET_CHAPTER_BY_ID
Retrieves detailed information about a specific chapter within a project in the elevenlabs platform. this endpoint is used to fetch metadata, content, or settings associated with a particular chapter, which could include text content for text-to-speech conversion, audio settings, or other chapter-specific data. it’s particularly useful for applications that need to manage or display information about individual chapters within larger text-to-speech or audio content projects. the endpoint requires both the project and chapter identifiers, ensuring precise retrieval of the desired chapter information.
Action Parameters
Action Response
ELEVENLABS_GET_MODELS_V_1_MODELS_GET
Retrieves a list of available text-to-speech models from the elevenlabs platform. this endpoint provides developers with information about the current models that can be used for voice synthesis. it should be used when initializing an application or when a user needs to choose a specific model for their text-to-speech tasks. the endpoint does not require any parameters, making it straightforward to query for up-to-date model information. however, it’s important to note that this endpoint only provides model details and does not perform any actual text-to-speech conversion.(DEPRECATED use get_models)
Action Parameters
Action Response
ELEVENLABS_STREAM_PROJECT_AUDIO
This endpoint streams audio from a specific project snapshot in the elevenlabs text-to-speech platform. it allows developers to retrieve and play audio content generated from a particular state of their project. the endpoint is particularly useful for applications that require real-time audio playback or need to access previously generated audio content. it supports optional conversion to mpeg format, which can be beneficial for broader compatibility across different audio players and systems. use this endpoint when you need to integrate dynamic audio streaming from your elevenlabs projects into your applications.
Action Parameters
Action Response
ELEVENLABS_GET_VOICES
Retrieves a comprehensive list of all available voices on the elevenlabs text-to-speech platform. this endpoint should be used when you need to explore the full range of voice options for text-to-speech synthesis, including both premium and cloned voices. it provides essential information about each voice, such as unique identifiers, names, and potentially additional metadata like language and gender. this tool is particularly useful for applications that need to offer voice selection to users or for developers who want to programmatically access the entire voice catalog. note that while this endpoint returns all voices, it does not provide audio samples or detailed voice characteristics; those may need to be accessed through separate endpoints.
Action Parameters
Action Response
ELEVENLABS_REMOVE_RULES_FROM_THE_PRONUNCIATION_DICTIONARY
Removes specified pronunciation rules from an existing pronunciation dictionary in the elevenlabs text-to-speech platform. this endpoint allows users to fine-tune the pronunciation of words by deleting unwanted rules without affecting the entire dictionary. it should be used when specific pronunciation rules are no longer needed or when correcting errors in the dictionary. this operation is permanent and cannot be undone, so care should be taken when removing rules. the endpoint does not provide a way to add new rules or modify existing ones; it is specifically for rule removal.
Action Parameters
Action Response
ELEVENLABS_GET_PROJECT_BY_ID
Retrieves detailed information about a specific project within the elevenlabs platform. this endpoint allows developers to fetch project metadata, associated voices, and other relevant details using the project’s unique identifier. it should be used when you need to access or display information about a particular project, such as its name, creation date, or associated resources. the endpoint does not modify any project data and is primarily for read-only operations. keep in mind that the specific details returned may depend on the user’s access level and the project’s visibility settings.
Action Parameters
Action Response
ELEVENLABS_CREATES_AUDIONATIVE_ENABLED_PROJECT
Creates a new audio-native project in the elevenlabs platform, allowing for the generation of an embedded audio player that automatically voices web page content using elevenlabs’ text-to-speech service. this endpoint is used to set up a customizable audio player with various appearance and behavior options, including voice selection, text-to-speech model, and player styling. it’s particularly useful for content creators, publishers, or developers looking to add audio versions of their text content to web pages. the endpoint requires a project name and content file, with numerous optional parameters for fine-tuning the player’s appearance and functionality. it’s important to note that while the project is created immediately, the audio conversion may not occur automatically unless specified.
Action Parameters
Action Response
ELEVENLABS_DELETE_PROJECT
Deletes a specific project from the user’s account in the elevenlabs platform. this endpoint should be used when a user wants to permanently remove a project and all its associated data. it’s important to note that this action is irreversible, and once a project is deleted, it cannot be recovered. use this endpoint with caution, ensuring that the project is no longer needed before deletion. the endpoint requires the project’s unique identifier and will not provide any information about the deleted project upon successful execution.
Action Parameters
Action Response
ELEVENLABS_GET_SSO_PROVIDER_ADMIN
Retrieves the current single sign-on (sso) provider configuration for the elevenlabs admin panel. this endpoint is designed for administrative use to fetch details about the configured sso provider, which may include information such as the provider type, authentication endpoints, and other relevant settings. it should be used when administrators need to review or verify the current sso setup. the endpoint does not modify any settings and is read-only. note that this endpoint is likely restricted to users with administrative privileges and may require special authentication.
Action Parameters
Action Response
ELEVENLABS_GET_VOICES_V_1_VOICES_GET
Retrieves a comprehensive list of all available voices on the elevenlabs text-to-speech platform. this endpoint should be used when you need to explore the full range of voice options for text-to-speech synthesis, including both premium and cloned voices. it provides essential information about each voice, such as unique identifiers, names, and potentially additional metadata like language and gender. this tool is particularly useful for applications that need to offer voice selection to users or for developers who want to programmatically access the entire voice catalog. note that while this endpoint returns all voices, it does not provide audio samples or detailed voice characteristics; those may need to be accessed through separate endpoints.(DEPRECATED use get_voices)
Action Parameters
Action Response
ELEVENLABS_DELETE_VOICE
Deletes a specific voice from the elevenlabs platform using its unique identifier. this endpoint permanently removes the voice associated with the provided voice id from the user’s account and the elevenlabs system. it should be used when a custom voice is no longer needed or to manage the user’s voice inventory. this operation is irreversible, so users should be certain they want to delete the voice before making the api call. the endpoint does not return the deleted voice data and cannot be used to temporarily disable or archive a voice.
Action Parameters
Action Response
ELEVENLABS_GET_VOICE_SETTINGS
Retrieves the current settings for a specific voice in the elevenlabs text-to-speech system. this endpoint allows developers to fetch the customizable parameters that affect the voice’s output, such as stability, similarity to the original voice, style exaggeration, and speaker boost. it should be used when you need to check or verify the current configuration of a voice before generating speech or when planning to modify these settings. the endpoint provides a snapshot of the voice’s current behavior-influencing factors but does not return audio samples or voice characteristics.
Action Parameters
Action Response
ELEVENLABS_UPDATE_PRONUNCIATION_DICTIONARIES
Updates the pronunciation dictionaries associated with a specific project in the elevenlabs text-to-speech platform. this endpoint allows you to apply one or more pronunciation dictionaries to ensure accurate pronunciation of words and phrases in your text-to-speech conversions. it’s particularly useful when you need to customize pronunciation for specific terms, names, or industry jargon within a project. the endpoint supports adding multiple dictionaries, which can be specified using either json body or form-data. however, be aware that the current ui only displays the first dictionary in the list. use this endpoint when you need to modify or enhance the pronunciation accuracy for a project, especially for specialized content or multilingual applications.
Action Parameters
Action Response
ELEVENLABS_VOICE_GENERATION_PARAMETERS
Retrieves the available parameters and settings for voice generation using the elevenlabs api. this endpoint provides developers with information about the configurable options when generating voices, such as available voice ids, model ids, and customizable voice settings. it should be used when planning voice generation tasks or when needing to understand the range of options available for voice customization. this endpoint does not actually generate any audio; it only provides metadata about the voice generation process.
Action Parameters
Action Response
ELEVENLABS_DELETE_HISTORY_ITEM
Deletes a specific history item from the user’s elevenlabs account. this endpoint permanently removes the selected item from the history, including its associated metadata and audio file. it should be used when a user wants to clean up their history or remove sensitive or unnecessary items. the deletion is irreversible, so caution should be exercised when using this endpoint. it’s important to note that this operation only affects the user’s history and does not impact any other data or settings in their account.
Action Parameters
Action Response
ELEVENLABS_TEXT_TO_SPEECH_STREAM
Converts text into speech using a voice of your choice and returns audio as an audio stream.
Action Parameters
Action Response
ELEVENLABS_REDIRECT_TO_MINTLIFY
Retrieves the comprehensive api documentation for the elevenlabs text-to-speech platform. this endpoint provides developers with detailed information about all available endpoints, their parameters, expected responses, and usage guidelines. it is essential for understanding the capabilities of the elevenlabs api and how to integrate it into applications. the documentation likely covers various aspects such as voice generation, streaming audio, voice settings, and model support. use this endpoint when you need to explore the api’s features or require specific implementation details for any elevenlabs service.
Action Parameters
Action Response
ELEVENLABS_GET_PRONUNCIATION_DICTIONARIES
Retrieves a list of all available pronunciation dictionaries in the user’s account. this endpoint is useful for developers who want to customize the pronunciation of specific words or phrases in their text-to-speech applications. pronunciation dictionaries can be applied to improve the accuracy and naturalness of speech synthesis, especially for domain-specific terms, acronyms, or proper nouns. the endpoint returns information about each dictionary, which can be used in subsequent api calls for text-to-speech conversion. it’s particularly valuable when working with multilingual content or specialized vocabularies.
Action Parameters
Action Response
ELEVENLABS_GET_PLS_FILE_WITH_A_PRONUNCIATION_DICTIONARY_VERSION_RULES
This endpoint allows you to download a specific version of a pronunciation dictionary from the elevenlabs platform. pronunciation dictionaries are essential for controlling how words are pronounced in text-to-speech applications, using either phonemes (ipa or cmu arpabet) or aliases. use this endpoint when you need to retrieve the actual dictionary file for offline use, backup, or to inspect its contents. the downloaded file will likely be in the .pls format, which is the standard format for pronunciation dictionaries in elevenlabs. this endpoint is particularly useful for developers who need programmatic access to their pronunciation dictionaries for integration into their own systems or for maintaining consistent pronunciations across different projects.
Action Parameters
Action Response
ELEVENLABS_DUB_A_VIDEO_OR_AN_AUDIO_FILE
This endpoint allows you to dub a video or audio file into a target language using elevenlabs’ advanced text-to-speech synthesis. it supports both automatic and manual dubbing modes, with options for voice cloning, speaker detection, and studio editing. the tool is ideal for content creators, filmmakers, and developers looking to localize audio content or create multilingual versions of their media. it offers flexibility in input methods, including direct file upload or url-based source retrieval, and provides control over dubbing parameters such as language selection, speaker count, and output quality. the endpoint can handle complex dubbing scenarios, including separate foreground and background audio processing when used with csv metadata input.
Action Parameters
Action Response