Add ElevenLabs to your AI agent

Use to retrieve all details for a specific project, including its chapters and their conversion statuses, by providing the project's unique ID.

Fetches a list of all projects and their details associated with the user's ElevenLabs account; this is a read-only operation.

Tool to retrieve usage metrics for the current user or entire workspace. Returns time-series data with configurable aggregation intervals and breakdown types. Use when analyzing character usage patterns, tracking consumption by voice, user, or other dimensions over time.

Tool to list dubbing projects you have access to. Use when you need to retrieve dubs, check their status, or paginate through available dubbing projects.

Tool to register a Twilio call and return TwiML to connect the call to an ElevenLabs Conversational AI agent. Use when you need to integrate ElevenLabs agents with your own Twilio infrastructure for inbound or outbound calls.

Deprecated by the provider; this endpoint will be removed on October 31, 2026 (2026-10-31). For new simulations, use ELEVENLABS_CREATE_CONVAI_AGENT_TESTING to create a simulation test, then ELEVENLABS_RUN_AGENT_TESTS to run it and ELEVENLABS_GET_TEST_INVOCATION to retrieve its result. Replacement simulations use a different asynchronous contract with a 50-turn maximum; this action retains its existing inputs and outputs. Run a simulated conversation between an agent and an AI user to test agent behavior with specific scenarios or evaluate conversation flow. Returns full transcript with analysis including success metrics and conversation summary.

Tool to update content for an Audio Native project by uploading a text or HTML file. Use when you need to refresh or change the content of an existing Audio Native project. Optionally auto-convert to audio and auto-publish the new snapshot.

Tool to update an existing ElevenLabs Conversational AI agent's settings. Use when you need to modify an agent's configuration, such as changing its name, conversation settings, workflow, or platform settings.

Adds a new pronunciation dictionary from a lexicon file to improve speech synthesis accuracy.

Add an existing workspace member to a group by email. Requires group_members_manage permission and your own ElevenLabs connection.

Tool to import/register a Twilio phone number or SIP trunk into ElevenLabs Agents Platform. Use when you need to provision a phone number for outbound calls and ELEVENLABS_GET_AGENT_DETAILS returns empty phone_numbers. This does NOT purchase a new number; it imports an existing provider configuration into your ElevenLabs workspace.

Tool to create a new pronunciation dictionary from provided rules for ElevenLabs text-to-speech. Use when you need to define custom pronunciations for specific words or phrases to improve speech accuracy. Supports both alias rules (simple text replacements) and phoneme rules (IPA phonetic notation).

Adds one or more custom pronunciation rules (alias or phoneme) to an existing pronunciation dictionary.

Adds an existing, shareable voice to a specified user's ElevenLabs account library under a new custom name, requiring the user's public ID and the voice ID.

Add a source transcript segment to an Enterprise dubbing project. The span must lie within the source media, last 0.1–25 seconds, and not overlap another segment by the same speaker. Bumps the revision, discards affected translations in every target language, and marks completed targets stale. Audio changes only after regenerating a target. Requires your own ElevenLabs connection.

Adds a custom voice by uploading audio samples for voice cloning. Requires a name and at least one audio file. Recommended: 1-2 minutes of clear audio without background noise. Supported formats: mp3, wav, ogg. Returns a voice_id that can be used for text-to-speech after processing completes.

Add audio samples to an existing professional voice clone (PVC). Requires your own ElevenLabs connection. Returns the added sample metadata.

Add a voice to a collection you can edit. Adding an existing member succeeds without changes. Requires your own ElevenLabs connection.

Align an audio file to a supplied transcript and return character and word timestamps with alignment loss scores. Diarization is not supported. Requires your own ElevenLabs connection.

Add approval for a specific MCP tool when using per-tool approval mode. Requires your own ElevenLabs connection; returns the updated server configuration.

Assign 1–50 existing workspace tags to a conversation. Already assigned tags are ignored. Requires your own ElevenLabs connection.

Tool to assign or unassign an existing imported phone number to an agent by updating the phone number's assigned agent. Use when you need to programmatically route inbound calls to a specific agent or change agent assignment for a phone number.

Delete 1–20 knowledge-base documents or folders, with independent outcomes per ID. Force also removes agent references and recursively deletes folder contents. Requires your own ElevenLabs connection.

Tool to calculate expected number of LLM tokens needed for a conversational AI agent. Use when estimating costs for an agent based on knowledge base size, prompt length, and RAG configuration.

Tool to calculate expected LLM usage costs for conversational AI agents. Use when you need to estimate pricing for different LLM models based on prompt length, knowledge base size, and RAG configuration.

Tool to cancel a running batch call and set all recipients to cancelled status. Use when you need to stop an ongoing batch calling campaign.

Cancel a crawl job and delete all associated documents and folders. Requires your own ElevenLabs connection.

Cancel all pending runs in a test invocation using its ID from a test run. Requires your own ElevenLabs connection.

Append a resolution comment to a ticket and return the updated ticket. Requires viewer access to the ticket's agent and your own ElevenLabs connection.

Append a comment about a transcript turn to a triage ticket and return the updated ticket. Requires viewer access to the ticket's agent and your own ElevenLabs connection.

Compose a song from a prompt or composition plan and return audio plus its song ID. Requires your own ElevenLabs connection.

Compose music from a prompt or composition plan and return downloadable audio plus structured song metadata. Optional word timestamps and waveform preview. Requires your own ElevenLabs connection.

Trigger RAG indexing for a knowledge-base document, or return its current status if already indexed. Requires your own ElevenLabs connection.

Converts the textual content of a chapter, identified by `chapter_id` within a `project_id`, into audio format.

Converts an existing ElevenLabs Studio project, including all its chapters and using its configured settings and voices, into speech.

Transform audio into a target voice while preserving emotion, timing and delivery. Upload the source audio and choose a target voice ID. Requires your own ElevenLabs connection.

Finalizes the creation of a voice using its `generated_voice_id` from a previous generation step by assigning a name, description, and optional labels.

Create an ElevenLabs agent branch from an existing agent version.

Create a procedure in an ElevenLabs agent branch draft working set.

Create a new draft for an existing agent branch with conversation config, platform settings, workflow, name and optional tags. Requires your own ElevenLabs connection.

Raise a manual follow-up ticket against an agent, without a conversation. Requires viewer access to the agent and your own ElevenLabs connection. When title is omitted it is derived from qa_comment.

Queue speech synthesis with Flash v2.5, Multilingual v2 or Eleven v3. Returns a pending generation ID for polling via the corresponding GET endpoint; optional flows webhooks deliver completion or failure. Charged per character by ElevenLabs. Requires your own ElevenLabs connection.

Create a blank Studio chapter or initialize it from a URL in an existing project. Requires your own ElevenLabs connection.

Tool to create a new ElevenLabs Conversational AI agent response test. Use when you need to set up automated testing for agent responses, tool calls, or conversation simulations. Supports three test types: 'llm' for response validation, 'tool_call' for tool execution verification, and 'simulation' for full conversation testing.

Deprecated by the provider; no sunset date is announced. Add documentation to ElevenLabs Conversational AI knowledge base by uploading a file or referencing a webpage URL. Use when you need to provide reference materials or documentation that agents can access during conversations. Exactly one of 'file' or 'url' must be specified.

Tool to create a knowledge base document from an uploaded file for ElevenLabs Conversational AI agents. Use when you need to provide documentation or reference material that agents can access during conversations. The uploaded file content will be indexed and made available to agents for answering user queries.

Tool to create a folder in the ElevenLabs ConvAI knowledge base for organizing documents. Use when you need to group related documents together in a hierarchical structure.

Tool to compute or retrieve RAG indexes for multiple knowledge base documents in batch. Use when you need to enable semantic search on multiple knowledge base documents for conversational AI agents. This endpoint creates embeddings if missing or returns existing indexes, supporting up to 100 documents per request.

Tool to create a knowledge base document with text content in ElevenLabs Conversational AI. Use when you need to add text-based information to the knowledge base for agent reference.

Tool to create a knowledge base document by scraping the given webpage. Use when you need to add a web page as a knowledge source for a conversational AI agent.

Tool to create a new secret for the ElevenLabs ConvAI workspace. Use when you need to securely store API keys, tokens, or other sensitive values that your conversational AI agents can reference.

Create a knowledge-base crawl job from a documentation URL, optionally filtering pages or enabling auto-sync. Returns the job ID and initial status, not the completed crawl. Requires your own ElevenLabs connection.

Create or update an agent's deployment using branch traffic percentages. Requires your own ElevenLabs connection.

Convert ordered text and voice pairs into one downloadable dialogue audio file.

Add a language target and queue a billed dub of an existing project. Generation starts when the project is ready and inherits its model. Requires your own ElevenLabs connection; enterprise translations can replace machine translation. Returns the queued target, not completed audio. Projects with webhooks emit dubbing_language_completed with output URLs.

Create an asynchronous dubbing project from uploaded media or a public URL. Incurs a minimum charge of one language before output exists. Returns a queued project; use webhooks to track preparation. Requires your own ElevenLabs connection.

Create a workspace environment. Variables without a value for it fall back to their production value. Requires your own ElevenLabs connection.

Create a workspace environment variable containing strings or references to existing secrets/auth connections. Requires your own ElevenLabs connection.

Queue an image generation using a selected model and optional reference images. Returns a pending generation ID; retrieve output with the image-generation GET endpoint. Requires your own ElevenLabs connection. ByteDance models require support approval.

Create an MCP server configuration using an HTTPS URL or existing workspace references. Requires your own ElevenLabs connection. Credential tokens and custom request headers/metadata are excluded by owner policy; configure those outside this tool. Existing auth-connection IDs remain supported.

Create a music finetune from uploaded audio, with a name, genre, optional tags and visibility. Requires your own ElevenLabs connection.

Generate background music from ordered video uploads, optionally guided by text, style tags or the video's audio. Returns audio or a ZIP of separate tracks. Requires your own ElevenLabs connection and an eligible subscription.

Tool to generate a music composition plan from a text prompt using ElevenLabs Music API. Use when you need to create a structured plan for music generation with defined styles, sections, and durations. The generated plan can be used as input for actual music generation or as a template for variations.

Create and auto-convert a Studio podcast from text or URLs with one or two voices. Audio generation incurs charges. Returns the project, not audio bytes. Requires your own ElevenLabs connection.

Create a Productions order in the workspace in the open state, ready to configure with items before submission. Optionally create a sandbox order that auto-progresses without producer intervention. Requires your own ElevenLabs connection.

Create a professional voice clone with metadata but no samples. Returns its voice ID; samples must be added separately. Requires your own ElevenLabs connection.

Create a service account in your ElevenLabs workspace with optional default sharing groups. Workspaces support 20 service accounts by default; Enterprise customers may request up to 100. Requires your own ElevenLabs connection.

Returns a list of shared voices similar to the provided audio sample. Use when you need to find voice matches based on audio characteristics. If neither similarity_threshold nor top_k is provided, default values will be applied.

Tool to generate a time-limited single-use token with embedded authentication for frontend clients. Use when you need secure, temporary access tokens for WebSocket connections or real-time services.

Create a Speech Engine resource connecting an upstream transcript WebSocket to configurable ASR, TTS and turn detection. Requires your own ElevenLabs connection.

Create a conversation tag for the workspace, with a title and optional description. Requires your own ElevenLabs connection.

Create a folder for organizing agent tests, optionally under a parent folder. Requires your own ElevenLabs connection.

Generate multi-voice dialogue with base64 audio, character timestamps and speaker segments. Requires your own ElevenLabs connection.

Create configuration overrides for one named MCP tool on an existing server. Returns the updated server configuration; an existing override produces HTTP 409. Requires your own ElevenLabs connection.

Raise a ticket about an agent's conversation performance for triage with Architect. Provide overall and/or turn-level comments. An existing open ticket can receive the comments and a higher priority. Requires your own ElevenLabs connection.

Queue a video generation using Veo, Seedance, or Creatify Aurora and return its pending ID. Retrieve output with the corresponding GET endpoint. ByteDance models require support approval. Requires your own ElevenLabs connection.

Create a voice collection with a title and icon; you become its admin. Requires your own ElevenLabs connection.

Create a saved voice from a previously generated voice preview. First obtain generated_voice_id through voice design or remix; provide a name and a 20–1000 character description. Requires your own ElevenLabs connection.

Tool to create a new webhook for the workspace with specified authentication type. Use when you need to configure a webhook endpoint to receive notifications from ElevenLabs. The webhook_secret returned should be stored securely for verifying webhook authenticity.

Creates an ElevenLabs AudioNative project, generating an embeddable audio player from a provided content file using text-to-speech, allowing customization of player appearance, audio settings, and conversion options.

Delete the draft for the specified agent branch. Requires your own ElevenLabs connection.

Remove an agent's custom hold audio so queued callers hear the default hold tone again. Requires your own ElevenLabs connection.

Delete an asset by ID. Requires your own ElevenLabs connection.

Irreversibly deletes a specific, existing chapter from an existing project, typically to remove unwanted or obsolete content.

Tool to permanently delete a Conversational AI agent by its unique identifier. Use when you need to remove an agent configuration from the ElevenLabs workspace.

Tool to delete an agent response test by ID. Use when you need to remove a test result or clean up test data.

Tool to permanently delete a batch call and all associated recipient records. Conversations remain in history. Use when cleaning up completed or cancelled batch calls.

Tool to delete a particular Conversational AI conversation by ID. Use when you need to remove a conversation from the system for cleanup, compliance, or data management purposes.

Tool to delete a document or folder from the knowledge base. Use when you need to remove a knowledge base document or folder that is no longer needed.

Tool to delete RAG index for a knowledge base document. Use when you need to remove semantic search indexing from a document to free up resources or when the document no longer needs to be indexed.

Tool to delete a workspace secret if it's not in use. Use when you need to remove unused secrets from the conversational AI workspace for security or cleanup purposes.

Tool to delete a conversational AI tool from the workspace by ID. Use when you need to remove a tool configuration that is no longer needed or to clean up outdated tool definitions.

Remove an uploaded file from a conversation before it has been used in that conversation. Requires your own ElevenLabs connection.

Delete a dubbing language target and its outputs, preserving the project and other languages. This cannot be undone; a running dub is still billed. Requires your own ElevenLabs connection.

Permanently deletes a dubbing project by its ID; this action is irreversible and the project cannot be recovered.

Permanently delete a dubbing project, every language target, and their stored media and outputs. This cannot be undone; an already running dub is still billed. Requires your own ElevenLabs connection.

Delete a workspace environment and remove its values from all environment variables. The 'production' environment cannot be deleted. Requires your own ElevenLabs connection.

Delete an environment variable and its values in all environments. Agents are not checked: deleting a variable still used by an agent causes its conversations to fail. Deletion is rejected while tools, MCP servers, or the workspace conversation initiation webhook use the variable. Requires your own ElevenLabs connection.

Permanently deletes a specific history item (including its audio file and metadata) using its `history_item_id`; this operation is irreversible and should be used with caution.

Invalidate an existing workspace email invitation. The delivered email remains in the recipient's inbox, but its invitation can no longer be activated. Requires workspace members invite permission and your own ElevenLabs connection.

Delete an audio isolation history item and its associated media files. Requires your own ElevenLabs connection.

Tool to delete a specific MCP server configuration from the workspace. Use when you need to remove an MCP server that is no longer needed or to clean up outdated configurations.

Delete a music finetune by ID and return its details. Requires your own ElevenLabs connection.

Tool to delete an imported phone number from the ElevenLabs workspace by ID. Use when you need to remove a phone number configuration for cleanup or to avoid stale configurations in automated environments.

Delete the user's procedure draft, resetting to the committed version. Requires your own ElevenLabs connection.

Permanently deletes a specific voice sample for a given voice ID; this action is irreversible.

Delete a previously generated, saved transcript by its ID. Requires your own ElevenLabs connection.

Delete a Speech Engine resource by its seng_ or agent_ ID. Requires your own ElevenLabs connection. Successful deletion returns no content.

Delete a conversation tag. Restricted to the tag owner or a workspace admin. Requires your own ElevenLabs connection.

Delete an agent test folder by ID. Set force=true to delete a non-empty folder and all its contents. Requires your own ElevenLabs connection.

Remove configuration overrides for one MCP tool and return the updated server configuration. Requires your own ElevenLabs connection.

Remove a source transcript segment from an Enterprise dubbing project. Bumps the project's revision, discards the affected translations in every language target, and marks completed targets stale. Audio changes only after regenerating a target. Requires your own ElevenLabs connection.

Delete an agent conversation ticket. Restricted to the ticket creator or a workspace admin. Requires your own ElevenLabs connection.

Permanently and irreversibly deletes a specific custom voice using its `voice_id`; the voice must exist and the authenticated user must have permission to delete it.

Delete a voice collection. Requires admin access to the collection. The voices in the collection are not deleted.

Delete a sample from a professional voice clone (PVC) using its voice and sample IDs. Requires your own ElevenLabs connection.

Delete a WhatsApp account by phone number ID. Requires your own ElevenLabs connection.

Tool to delete a specified workspace webhook by its ID. Use when you need to remove a webhook configuration that is no longer needed or to clean up webhook integrations.

Design voice previews from a descriptive prompt using your own ElevenLabs connection. Returns generated IDs and preview audio; save the preferred preview through /v1/text-to-voice to create a voice.

Downloads audio clips from history by ID(s), returning a single file or a ZIP archive, with an optional output format (e.g., 'wav'); provides only audio content, no metadata.

Legacy dry-run compilation of a branch's current procedure drafts into a workflow without persisting anything. Prefer saving an agent draft or publishing an agent: those operations compile automatically and return validation errors. This legacy endpoint remains available for existing callers and will eventually be deprecated. Requires your own ElevenLabs connection.

Dub a video or audio file into a specified target language, requiring 'file' or 'source_url', 'target_lang', and 'csv_file' if 'mode' is 'manual'.

Tool to create a new agent by duplicating an existing one. Use when you need to clone an agent's configuration. The new agent will inherit all settings from the original agent but can be given a new name.

Create a new speech engine by duplicating an existing seng_ or agent_ resource, optionally choosing a new name. Returns the new resource's ID and configuration. Requires your own ElevenLabs connection.

Edit an existing professional voice's name, language, description, or labels. Requires your own ElevenLabs connection.

Updates the name, audio files, description, or labels for an existing voice model. The voice_id must be for a voice owned by you (cloned voices). Premade/default voices cannot be edited. The 'name' field is required for all edit operations. This endpoint uses multipart/form-data format for the request body.

Edits key voice settings (e.g., stability, similarity enhancement, style exaggeration, speaker boost) for an existing voice, affecting all future audio generated with that voice ID.

Download recipients and conversation results for a terminal batch call as CSV. Optionally limit recipients to preview columns. Requires your own ElevenLabs connection.

Generates a unique, random ElevenLabs text-to-speech voice based on input text and specified voice characteristics.

Generate a downloadable sound effect from a text description, with optional duration and seamless looping. Requires your own ElevenLabs connection and consumes provider credits.

Retrieves the profile information for the authenticated ElevenLabs user (identified by API key).

Get metadata and recent versions for one Conversational AI agent branch.

Retrieve a procedure from an ElevenLabs agent branch HEAD or version.

Retrieve a user's procedure draft, falling back to branch HEAD when none exists.

Tool to retrieve available Conversational AI agents and outbound-capable Twilio phone numbers. Use when selecting an agent and phone number for outbound calls. Always reference agents by agent_id (stable identifier), not agent_name (mutable). Returns basic metadata only — conversation_config and webhook settings require a separate ConvAI agent API call. Pass agent_id and agent_phone_number_id directly to ELEVENLABS_OUTBOUND_CALL; IDs must be current and owned by the authenticated account.

Tool to get the current shareable link for a Conversational AI agent. Use when you need to retrieve the link URL for sharing the agent with others.

Read a specific agent version's commit, branch, ancestry and access metadata. Requires your own ElevenLabs connection.

Retrieve an asset by ID, including metadata and its temporary signed content URL (null while processing). Requires your own ElevenLabs connection.

Retrieve an asynchronous speech generation's status and its signed output URL once completed. Requires your own ElevenLabs connection.

Retrieves the audio content for a specific history item from ElevenLabs, using a `history_item_id` that must correspond to a previously generated audio.

Retrieves the audio for a given `sample_id` that must belong to the specified `voice_id`.

Tool to retrieve player settings for a specific Audio Native project. Use when you need to check the current configuration of an audio-native project, including display settings, colors, and status.

Read one page of workspace audit logs with optional time, actor and event filters. Requires enterprise tier and audit_log_read permission. Pass next_cursor as cursor to retrieve another page. Requires your own ElevenLabs connection.

Fetches comprehensive details for a specific chapter within a given project, including its metadata (name, ID), conversion status, progress, download availability, and content statistics.

Get a Studio chapter snapshot's metadata and character timing alignments by project, chapter and snapshot IDs. Requires your own ElevenLabs connection.

Retrieves all saved version snapshots for a specific chapter within a given project, enabling review of its history or reversion to prior states.

Retrieves a list of all chapters, their details, and conversion status for a project, useful for managing content or tracking progress.

Tool to retrieve the number of pages in a conversational AI agent's knowledge base. Use when you need to check the size of an agent's knowledge base content.

Tool to retrieve an ElevenLabs Conversational AI agent response test by its ID. Use when you need to fetch details of a specific test including its configuration, type, and test parameters.

Tool to retrieve the widget configuration for a Conversational AI agent. Use when you need to fetch display settings, colors, text content, and behavior options for an agent's embedded widget.

Tool to retrieve the live count of active ongoing Conversational AI conversations. Use when monitoring real-time conversation activity or checking current load.

Tool to retrieve all batch calls for the current workspace. Use when you need to list all batch calling campaigns, check their status, or find specific batch calls by name or agent.

Tool to retrieve the entire content of a document from the knowledge base. Use when you need to access or read the full text content of a knowledge base document.

Tool to retrieve a list of agents depending on a specific knowledge base document. Use when you need to identify which agents are using a particular document, either directly or transitively.

Tool to get details about a specific documentation making up the agent's knowledge base. Use when you need to retrieve information about a knowledge base document, including its content, type, and metadata.

Tool to retrieve RAG index overview including total size and usage information. Use when you need to check storage limits, monitor usage, or understand which embedding models are consuming space in knowledge base documents.

Tool to retrieve all RAG indexes for a specified knowledge base document. Use when you need to view the indexing status, models used, and usage statistics for a document's semantic search capabilities.

Tool to get a signed URL to download the original source file of a file-type document from the knowledge base. Use when you need to download the original file that was uploaded to create a knowledge base document.

Tool to retrieve knowledge base document summaries by their IDs. Use when you need to get summaries for multiple knowledge base documents in a single request.

Tool to retrieve all tools available for a specific MCP server configuration. Use when you need to inspect what tools an MCP server provides or verify tool availability before using them.

Tool to retrieve all MCP (Model Context Protocol) server configurations available in the workspace. Use when you need to list all registered MCP servers or check which servers are available for conversational AI agents.

Tool to retrieve detailed configuration for a specific phone number by ID. Use when you need to inspect a phone number's provider details, capabilities, agent assignments, or SIP trunk configuration.

Tool to retrieve all workspace secrets for the user. Use when you need to list stored secrets that can be used for authentication and integration with conversational AI agents. Supports pagination.

Tool to retrieve Convai settings for the workspace. Use when you need to inspect webhook configurations, RAG retention settings, or MCP server capabilities.

Tool to retrieve Convai dashboard settings for the workspace. Use when you need to inspect configured dashboard charts for monitoring conversational AI performance.

Tool to list all test invocations for a specific conversational AI agent with pagination support. Use when you need to retrieve test invocation history, check test results, or paginate through large sets of test runs.

Tool to retrieve the complete configuration for a specific conversational AI tool by ID. Use when you need to inspect a tool's settings, type, or usage statistics from the workspace.

Tool to retrieve a list of agents depending on a specific tool. Use when you need to identify which agents are using a particular tool in their configuration.

Download the audio recording of a particular conversation as a file. Requires your own ElevenLabs connection.

Tool to get a signed URL to start a conversation with an agent that requires authorization. Use when you need to obtain a secure WebSocket URL for initiating a conversation session.

Get a page of SIP messages associated with a conversation's phone call. Pass next_cursor as cursor to retrieve subsequent pages. Requires your own ElevenLabs connection.

Get a lightweight conversation summary, success result and short chat transcript. Tool calls, tool results and contextual updates are excluded. Use the full conversation endpoint for a complete transcript. Requires your own ElevenLabs connection.

Get an agent's latest discovered conversation topics or aggregate daily discovery runs over a time window. Rank topics by volume, sentiment, success rate or frustration; pass next_cursor as cursor to page. Requires your own ElevenLabs connection.

Get a knowledge-base crawl job's configuration, status and page progress by ID. Requires your own ElevenLabs connection.

Retrieves the ElevenLabs text-to-speech service's default voice settings (stability, similarity boost, style, speaker boost) that are applied when no voice-specific or request-specific settings are provided.

Retrieve a production order's delivered files and time-limited download URLs. Returns an empty list if the order is not yet completed. Requires your own ElevenLabs connection.

List agents depending on any of up to twenty knowledge-base documents or folders. Filter direct/transitive dependencies and paginate with next_cursor. Requires your own ElevenLabs connection.

Retrieves an existing dubbed audio file for a specific `dubbing_id` and `language_code`.

Get a dubbing language target's status, revisions, warnings and signed output URLs. URLs expire after one hour; re-read to refresh them. Prefer project webhooks over polling for completion. Requires your own ElevenLabs connection.

Get full dubbing project details, including language target IDs and source preparation status. Prefer a webhook subscription to polling for ready status. Requires your own ElevenLabs connection.

Retrieves metadata and status for a specific dubbing project by its ID.

Get a dubbing project's source transcript as editable segments, with speaker IDs, timings and revision. Available once the project is ready. Requires your own ElevenLabs connection.

Retrieves the transcript for a specific dubbing project and language in the requested format (SRT, WebVTT, or JSON). Use this when you need subtitles or detailed transcript data with timing information for a dubbed video or audio.

Retrieve one environment variable by ID, including its named values or secret/authentication references. Requires your own ElevenLabs connection.

Retrieves metadata for a list of generated audio items from history, supporting pagination and optional filtering by voice ID.

Retrieves detailed information (excluding the audio file) for a specific audio generation history item from ElevenLabs, using its unique ID.

Retrieve an image generation's status and its signed output URL when completed. Requires your own ElevenLabs connection.

List your audio isolation generations with optional title/text search and pagination. Page numbers apply only when search is provided. Requires your own ElevenLabs connection.

Tool to retrieve configuration overrides for a specific MCP tool within an MCP server. Use when you need to inspect the custom execution settings for individual tools.

Retrieve metadata and a time-limited download URL for previously uploaded order media. Requires your own ElevenLabs connection.

Retrieves metadata for a specific, existing pronunciation dictionary from ElevenLabs using its ID.

Retrieves a detailed list of all available ElevenLabs text-to-speech (TTS) models and their capabilities.

Retrieve a music finetune by ID, including training status, progress and failure reason. Requires your own ElevenLabs connection.

List chapter IDs with muted tracks in a Studio project. Returns the full list without pagination. Requires your own ElevenLabs connection.

Get one page of SIP messages for an imported phone number. Pass next_cursor as cursor to fetch another page. Requires your own ElevenLabs connection.

Retrieve full Productions order details, including item configurations and available quotes. Quotes may require polling before they become available. Requires your own ElevenLabs connection.

Get a Studio project snapshot's metadata, audio duration, and character alignments. Requires your own ElevenLabs connection.

Retrieves all available snapshots (saved states or versions) for an existing project, enabling history tracking, version comparison, or accessing specific states for playback/processing, particularly in text-to-speech workflows.

Downloads the Pronunciation Lexicon Specification (PLS) file for an existing version of a pronunciation dictionary from ElevenLabs, used to customize TTS pronunciation.

Retrieves a paginated list of pronunciation dictionaries, used to customize how specific words or phrases are pronounced by the text-to-speech (TTS) engine.

Retrieve a specific RAG chunk's ID, name and content from a knowledge-base document. Optionally select the embedding model used to retrieve it. Requires your own ElevenLabs connection.

Retrieve the first 30 seconds of a professional voice sample as base64 audio, optionally removing background noise. Requires your own ElevenLabs connection.

Retrieve the visual waveform of a professional voice clone sample. Requires your own ElevenLabs connection.

Retrieve a previously generated transcript by ID, including text, word timings and available channel details. Requires your own ElevenLabs connection.

Retrieve a workspace secret's name, ID, and dependency previews by ID. Returns metadata only, never the raw secret value. Requires your own ElevenLabs connection.

List one page of resources that depend on a secret, filtered by tools, agents, or phone numbers. Pass next_cursor as cursor to continue. Requires your own ElevenLabs connection.

Retrieve a speaker's separated sample audio as base64, with media type and duration. Requires your own ElevenLabs connection.

Tool to list all service accounts in the workspace. Use when you need to view service accounts, their associated API keys, or manage workspace access.

Retrieves a paginated and filterable list of shared voices from the ElevenLabs Voice Library.

Retrieve a professional voice sample's speaker separation status and detected speakers when complete. Requires your own ElevenLabs connection.

Retrieve one speech engine's configuration, including ASR, TTS, turn detection, privacy and access settings. Accepts a seng_ or agent_ ID. Requires your own ElevenLabs connection.

Retrieves the SSO provider configuration for a specified workspace, typically for review purposes, and will indicate if no configuration exists.

Get detailed information for one Studio project, including chapters, voices, assets, and conversion status. Supply its project ID and optionally its share ID. Requires your own ElevenLabs connection.

Tool to retrieve multiple agent response test summaries by their IDs. Use when you need to fetch summary information for multiple tests in a single request. Returns a dictionary mapping test IDs to their summary details including name, type, and timestamps.

Retrieve a conversation tag by ID, including its title, description, owner and creation time. Requires your own ElevenLabs connection.

Retrieve a flows template and its runnable versions' input/output ports. Accepts accessible shared-link and Explore templates, even when absent from template listings. Requires your own ElevenLabs connection.

Retrieve a template run's aggregate status and individual outputs, including completed media download URLs. Requires your own ElevenLabs connection.

Get an agent test folder by ID, including its folder path and direct child count. Requires your own ElevenLabs connection.

Get a test invocation by ID, including its test runs, results and bucketing status. Requires your own ElevenLabs connection.

Get a page of execution history for a tool, optionally filtered by agent, branch, error status and time. Pass next_cursor as cursor to fetch subsequent pages. Requires your own ElevenLabs connection.

Deprecated by the provider; no sunset date is announced. Retrieves the textual transcript for a specified dubbing project and language, if one exists for that language in the project.

Get a dubbing language target's source segments and translations in playback order. Available once the target has produced output; returns a conflict during its first dub. Requires your own ElevenLabs connection.

Get an agent conversation triage ticket by ID, including comments and status history. Requires your own ElevenLabs connection.

Retrieves detailed information about the authenticated ElevenLabs user's account, including subscription, usage, and status.

Retrieves detailed subscription information for the currently authenticated ElevenLabs user.

Get a captcha for professional voice clone (PVC) verification. The provider documents no response body. Requires your own ElevenLabs connection.

Retrieve a video generation's pending, generating, completed, or failed status. Completed generations include a signed output URL valid for about an hour. Requires your own ElevenLabs connection.

Retrieves comprehensive details for a specific, existing voice by its `voice_id`, optionally including its settings.

Get a voice collection you can access by its ID, including its title, icon, and your access role.

Retrieves the stability, similarity, style, and speaker boost settings for a specific, existing ElevenLabs voice using its `voice_id`.

Retrieves a list of all available voices along with their detailed attributes and settings.

Get a WhatsApp account's details, assigned agent and messaging settings by phone number ID. Requires your own ElevenLabs connection.

Tool to get metadata of a workspace resource by ID and type. Use when you need access control information, creator details, or sharing options for a specific resource.

Get workspace credit usage over time as a table, with optional grouping and filters. Requires your own ElevenLabs connection.

Tool to list all webhooks configured for the workspace. Use when you need to view existing webhook configurations or verify webhook settings.

Email an invitation to join your workspace. Acceptance consumes a subscription seat. Requires WORKSPACE_MEMBERS_INVITE permission and your own ElevenLabs connection; existing members return HTTP 400.

Send email invitations to multiple users to join your workspace. All addresses must belong to a verified domain. Accepting an invitation consumes a subscription seat; new users are prompted to create an account. Requires workspace member invite permission and your own ElevenLabs connection.

Remove background noise from an audio file and download the isolated vocals/speech. Uses your own ElevenLabs connection.

List procedure summaries attached to an ElevenLabs agent branch. Results omit procedure content; use Get Agent Branch Procedure with a returned procedure ID to read it.

List up to 100 agent branches. ElevenLabs returns a bounded result without a continuation parameter.

List an agent's conversation performance triage tickets for Architect, not end-user support tickets. Filter or search tickets and paginate with next_cursor while has_more is true. Requires your own ElevenLabs connection.

List workspace API requests as a table, filtering by time, columns, or search. Supply at least one time bound in Unix milliseconds. Results are timestamp-ordered; use sort to override the default. Requires your own ElevenLabs connection.

List workspace assets, newest first, optionally searching names. Returns one page; pass next_cursor as cursor for subsequent pages. Requires your own ElevenLabs connection.

List non-service-account workspace members for an agent's ticket assignment. Includes members without viewer access, flagged by has_access; grant access before assigning them. Requires your own ElevenLabs connection.

List speech generations created through the async API, newest first. Filter by status or model; pass next_cursor as cursor for subsequent pages. Requires your own ElevenLabs connection.

List filter presets, reverb environments, and background noises usable in Text to Speech, Text to Dialogue, and agent audio_effects configurations. Requires your own ElevenLabs connection.

List all snapshots of a Studio chapter, including IDs, names and creation times. Snapshots are created automatically when a chapter is converted and can be downloaded as audio using the snapshot audio actions. Requires your own ElevenLabs connection.

Tool to list all agent response tests with pagination support and optional search filtering. Use when you need to retrieve available tests, search tests by name, or paginate through large test collections.

List language models available for configuring ElevenLabs Conversational AI agents.

List distinct conversation users with contact details and sentiment aggregates. Filter and sort results, then pass next_cursor as cursor to fetch another page. Requires your own ElevenLabs connection.

List the user's ongoing and recent knowledge-base crawl jobs. Pass next_cursor as cursor to fetch another page, and include_job_ids to include additional jobs. Requires your own ElevenLabs connection.

List an agent's deployment traffic split history, newest first. Use page and page_size to paginate. Requires your own ElevenLabs connection.

List a dubbing project's language targets and statuses, with signed output URLs once available. Pass next_cursor as cursor to fetch the next page. Requires your own ElevenLabs connection.

List accessible workspace dubbing projects with cursor pagination, newest first by default. Listed projects have no language IDs; fetch the project or list its language targets for those. Requires your own ElevenLabs connection.

List one page of workspace environment variables, optionally filtering by label, environment, or type. Use next_cursor to retrieve subsequent pages. Requires your own ElevenLabs connection.

List workspace environments, including production, with optional last-update and creator details. Returns the full list without pagination. Requires your own ElevenLabs connection.

List image generations created through the API, newest first, with optional status and model filters. Pass next_cursor as cursor to retrieve another page. Requires your own ElevenLabs connection.

List all workspace members, including locked members, with their roles and owner status. Service accounts are excluded. Requires your own ElevenLabs connection.

List your own, workspace-shared, and ElevenLabs-curated music finetunes with optional filters and sorting. Returns one page; pass next_cursor as cursor to continue. Requires your own ElevenLabs connection.

Tool to list all imported phone numbers in the workspace. Use when you need to find available phone numbers, check their capabilities (inbound/outbound), or verify which agent is assigned to a number.

List available production languages for dubbing, subtitles or transcription. Returns single languages or source-to-destination pairs. Requires your own ElevenLabs connection.

List Productions orders in your workspace, optionally filtering by statuses and creation dates. Use page_size and offset to paginate. Requires your own ElevenLabs connection.

List a page of RAG chunks for a knowledge base document and embedding model. Pass next_cursor as cursor to retrieve another page. Requires your own ElevenLabs connection.

List a page of Speech Engines with voice, tags, timestamps and access information. Filter by name or sort results; pass next_cursor as cursor to retrieve the next page. Requires your own ElevenLabs connection.

List workspace conversation tags, newest first. Returns one page; pass next_cursor as cursor to continue. Requires your own ElevenLabs connection.

List a template's runs created through the public API, newest first. Use next_cursor as cursor to paginate and version_id to filter. Requires your own ElevenLabs connection.

List published flow templates in your workspace and their runnable versions' input/output schemas. Follow next_cursor while has_more is true, even for empty pages. Link-shared or other-workspace Explore templates are not listed. Requires your own ElevenLabs connection.

List video generations created through the API, newest first, optionally filtered by status or model. Pass next_cursor as cursor to fetch another page. Requires your own ElevenLabs connection.

List available accents in the shared voice library, optionally filtered by language and model. Requires your own ElevenLabs connection.

List all voice collections you can access, sorted by title, including your access role. The endpoint returns the full list without pagination.

Tool to list all WhatsApp accounts in the workspace. Use when you need to view available WhatsApp Business accounts, check which agents are assigned to WhatsApp numbers, or retrieve WhatsApp phone number details.

List all groups in the workspace, including membership, permissions, limits and SCIM details. Returns a map without pagination. Requires your own ElevenLabs connection.

List conversation triage tickets across the workspace, omitting agents you cannot access. Supports filters, search, sorting and cursor pagination. Requires your own ElevenLabs connection.

Merge an agent's source branch into a target branch. By default, archives the source after merging; force overrides timestamp-based conflict resolution. Requires your own ElevenLabs connection.

Merge open tickets of the same agent into a pending, in-progress, or resolved ticket. Moves their conversations, raises priority to the highest, and preserves sources as merged. Requires viewer access to the agent and your own ElevenLabs connection.

Tool to move multiple documents or folders from one folder to another in the knowledge base. Use when you need to reorganize multiple knowledge base items at once by moving them to a different folder or to the root level.

Tool to move a knowledge base document or folder to a different folder. Use when you need to reorganize your knowledge base by moving entities between folders or to the root level.

Move multiple tests or folders to a destination folder, or to root when omitted. Requires your own ElevenLabs connection.

Tool to place an outbound call via SIP trunk. Use when you need to initiate a voice call through an ElevenLabs agent after obtaining required IDs. Prerequisites: - The API key must have Conversational AI (convai) permissions enabled. For write operations like initiating calls, ensure your API key has the appropriate convai write scope. - A valid SIP trunk phone number must be configured for outbound calls in ElevenLabs. - The SIP trunk must have valid outbound configuration with proper address and credentials. - The agent must be properly configured in the Conversational AI platform.

Retrieve one page of phone numbers with optional search, agent, provider and sorting filters. Pass next_cursor as cursor to fetch the next page. Requires your own ElevenLabs connection.

Preview merging a source branch into a target branch without performing the merge. Returns the merged agent configuration and conflicting fields for an accurate diff before confirming. Force makes source changes win conflicts regardless of timestamps. Requires your own ElevenLabs connection.

Preview pulling source-branch changes into an agent branch without modifying it. Defaults to the agent's main branch as the source. Includes conflicting field paths, structured conflict values, and the merged configuration. Requires your own ElevenLabs connection.

Run an ad-hoc query against an agent's knowledge base RAG index and return ranked chunks. Read-only: no conversation is created. Retrieval internals may evolve. Requires your own ElevenLabs connection.

Pull changes from a source branch (default: main) into this branch as a new version, preserving this branch's own changes on conflicts. Requires your own ElevenLabs connection.

Retrieves the content of the official ElevenLabs API documentation page hosted on Mintlify.

Refresh an existing URL knowledge-base document by re-fetching content from its source URL. Returns the updated document. Requires your own ElevenLabs connection.

Re-dub an Enterprise dubbing target from its edited transcript, synthesizing only edited regions. Charges apply after the free-regeneration allowance. Acceptance is asynchronous: the target returns to processing and emits dubbing_language_completed to the project's configured webhooks with output URLs when complete. Returns a conflict if no edits exist, without dispatching or charging. Requires your own connection.

Register media with a production order by uploading a file or supplying a URL. Use the returned media ID when adding order items. Requires your own ElevenLabs connection.

Remix an existing voice using a prompt and return voice previews. Save the preferred generated_voice_id using the create-voice endpoint. Requires your own ElevenLabs connection.

Remove a workspace member from a specified group by email. Requires group_members_manage permission and your own ElevenLabs connection.

Remove an item from an open production order. Requires your own ElevenLabs connection.

Remove a procedure from an agent's draft working set. Removing a folder cascades to its entire subtree and is rejected if an outside procedure hands off into it. Requires your own ElevenLabs connection.

Permanently removes exact-match pronunciation rules from a specified ElevenLabs pronunciation dictionary using a list of rule strings; non-matching rule strings are ignored and this action cannot add or modify rules.

Remove approval for a specific MCP tool when using per-tool approval mode. Returns the updated server configuration. Requires your own ElevenLabs connection.

Remove a voice from a collection without deleting the voice itself. Requires editor access to the collection and your own ElevenLabs connection.

Replace all existing rules in a pronunciation dictionary with the provided alias and phoneme rules. Requires your own ElevenLabs connection.

Replicate an Instant Voice Clone or Voice Design voice to another data residency. Available on the central environment only. The target workspace must share the source's consolidated billing group. Requires source voice admin access and VOICES_WRITE in the source workspace; human users also need VOICES_WRITE in the target workspace. Requires your own ElevenLabs connection.

Request manual verification for a professional voice clone (PVC) by submitting verification documents and optional explanatory text. Requires your own ElevenLabs connection.

Resolve a Slack message or Zendesk ticket URL for an agent and return the existing conversation's details. Requires your own ElevenLabs connection.

Tool to resubmit specific test runs from a test invocation for a conversational AI agent. Use when you need to re-run failed tests or specific test cases from a previous test invocation.

Tool to retry a batch call, calling failed and no-response recipients again. Use when you need to retry unsuccessful calls from a previous batch calling campaign.

Tool to run selected tests on a conversational AI agent with optional configuration overrides. Use when you need to execute automated tests on an agent to validate responses, tool calls, or conversation flows. Supports running up to 200 tests in a single invocation with optional branch-specific or configuration override testing.

Re-run a conversation's analysis with the agent's current evaluation criteria and data collection settings. Returns the full conversation, including updated analysis. Requires your own ElevenLabs connection.

Rerun one evaluation criterion for an existing conversation. Returns the updated full conversation, including its analysis and transcript. Scope selects conversation-level or agent-level evaluation. Requires your own ElevenLabs connection.

Start a flows template run using input-port values and an optional snapshot version. Returns initial run state, not finished results. Prefer a configured webhook for completion, or poll the run at modest intervals. Requires your own ElevenLabs connection.

Search conversation transcript messages using full-text and fuzzy matching. Returns matching chunks, highlights and a next-page cursor; pass next_cursor as cursor to continue. Requires your own ElevenLabs connection.

Fuzzy text search over knowledge-base document content. Filter by document type and use next_cursor to fetch subsequent pages. Requires your own ElevenLabs connection.

Search available voices by text, labels, type or collection, with sorting and cursor pagination. Pass next_page_token from the response while has_more is true. Requires your own ElevenLabs connection.

Search workspace groups by name, returning group IDs and member emails. Multiple or no groups may match. Requires your own ElevenLabs connection.

Search conversation transcripts by semantic meaning and intent, rather than exact keywords. Optionally filter by agent and branch. Returns one page of scored message chunks; pass next_cursor as cursor to continue. Requires your own ElevenLabs connection.

Send like/dislike feedback within five minutes of a conversation ending. Requires your own ElevenLabs connection.

Send an outbound WhatsApp template message using an ElevenLabs agent and WhatsApp phone number. Returns the conversation ID. Requires your own ElevenLabs connection.

Separate an audio file into individual stems and download a ZIP archive. Latency depends on audio length. Requires your own ElevenLabs connection.

Start speaker separation for a professional voice sample. Returns the start request status, not the separated audio. Requires your own ElevenLabs connection.

Tool to set or update the avatar image for a Conversational AI agent displayed in the widget. Use when you need to customize the visual appearance of an agent by uploading a profile image.

Upload custom hold audio for callers in an agent's concurrency wait queue, replacing any previous clip. Accepts MP3 or WAV up to 40 MB and 180 seconds. Requires your own ElevenLabs connection.

Set pronunciation dictionaries on a Studio project. By default affected text is marked for reconversion. Requires your own ElevenLabs connection.

Grant a workspace resource role to a user, group, or service account API key, overriding its existing role. Supply only one target: user_email, group_id, or workspace_api_key_id. The caller must have admin access to the resource. Requires your own ElevenLabs connection.

Converts an input audio file to speech using a specified voice; if a `model_id` is provided, it must support speech-to-speech conversion.

Converts an input audio stream to a different voice output stream in real-time, using a specified speech-to-speech model.

Start an outbound phone call via the agent's configured Exotel number. Returns success, a provider message, conversation ID and Exotel CallSid. Requires your own ElevenLabs connection.

Start an outbound phone call via the agent's configured Twilio number. Returns success, a provider message, conversation ID and Twilio call SID. Requires your own ElevenLabs connection.

Start an outbound WhatsApp call using an agent and permission request template. Requires your own ElevenLabs connection.

Tool to remove background noise from audio and stream the isolated result. Use when you need to clean up audio recordings by isolating vocals/speech and removing unwanted background noise. The audio file must be at least 4.6 seconds long.

Streams the audio for a specified chapter snapshot from an ElevenLabs project, optionally converting the output to MPEG format.

Deprecated by the provider; this endpoint will be removed on October 31, 2026 (2026-10-31). For new simulations, use ELEVENLABS_CREATE_CONVAI_AGENT_TESTING to create a simulation test, then ELEVENLABS_RUN_AGENT_TESTS to run it and ELEVENLABS_GET_TEST_INVOCATION to retrieve its result. Replacement simulations use a different asynchronous contract with a 50-turn maximum; this action retains its existing inputs and raw SSE output. Run a simulated conversation between an agent and a simulated user, streaming back partial lists of messages and a final conversation analysis.

Convert ordered text and voice-ID pairs into multi-voice speech and return the streamed audio as a downloadable file. Requires your own ElevenLabs connection.

Stream a composed song from a prompt or composition plan and return downloadable audio plus its song ID. Requires your own ElevenLabs connection.

Generate music with detailed metadata using your own ElevenLabs connection. Collects the documented SSE stream into ordered named events: audio_chunk data contains base64 audio plus optional word timestamps and waveform slices. Returns song_id and preserves all metadata. Multipart responses, if supplied, are separated into downloadable parts and JSON metadata.

Streams audio from a specific project snapshot, optionally converting it to MPEG format.

Download streamed audio from an existing Studio project snapshot, optionally converted to MPEG. Requires your own ElevenLabs connection.

Generate multi-speaker dialogue and collect its JSON stream as ordered audio chunks with character timestamps and voice segments. Requires your own ElevenLabs connection; the result buffers the complete stream.

Convert text to speech with character timestamps using a chosen voice. Collects the JSON stream into ordered events with base64 audio chunks. Requires your own ElevenLabs connection.

Convert uploaded audio to a target voice, preserving emotion, timing and delivery. Downloads the audio stream as a file. Requires your own ElevenLabs connection.

Download streaming MPEG audio for a voice preview created via /v1/text-to-voice/design. Requires your own ElevenLabs connection.

Archives an existing project snapshot by its ID, creating a permanent, immutable, and typically irreversible copy of its state.

Tool to submit a batch call. Use when you need to initiate multiple calls (voice or WhatsApp) at once. Triggers real outbound calls immediately (if no scheduled_time_unix is set) or at the scheduled time — always confirm recipient list and call count with the user before executing.

Submit an open production order with at least one item for processing. Submission charges the workspace and prevents further item modifications. To review the quote first, poll the order details until the quote is ready. Requires your own ElevenLabs connection.

Generate speech with character-level timestamps for audio/text synchronization, returning base64 audio and original/normalized alignments. Requires your own ElevenLabs connection; model, voice and format availability depends on your plan.

Converts text to speech using a specified ElevenLabs voice and model, returning a downloadable audio file (use ELEVENLABS_TEXT_TO_SPEECH_STREAM for streaming instead). Keep `voice_id`, `model_id`, and `output_format` consistent across all chunks to avoid audible artifacts when concatenating. Some voice/model/format combinations require specific subscription tiers; test with a short sample before full runs. HTTP 429 on burst batches; respect `Retry-After` headers.

Converts text through the provider streaming endpoint and returns a downloadable audio file. Provider logging and history remain enabled by default. Allows latency optimization, specific output formats (some tier-dependent), and custom pronunciations; ensure the chosen model supports text-to-speech and text is preferably under 5000 characters. Keep voice_id, model_id, and output_format consistent across multi-chunk sessions to avoid audio artifacts.

Start professional voice clone (PVC) training for an existing voice, optionally choosing its model. Requires your own ElevenLabs connection.

Transcribe one uploaded file or public media URL with ElevenLabs.

Remove a single tag from a conversation. Requires your own ElevenLabs connection.

Remove an existing workspace resource role from a user, group, or service account API key. Pass only the user email, group ID, or workspace API key ID for the intended recipient. Requires admin access to the resource; its creator's permissions cannot be removed. Requires your own ElevenLabs connection.

Update metadata for an ElevenLabs Conversational AI agent branch.

Replace an ElevenLabs agent branch procedure draft.

Find an existing Audio Native project matching a page URL, extract its content, update the project, and queue conversion and auto-publishing. Requires your own ElevenLabs connection.

Update a Studio chapter's name or structured text-to-speech content by project and chapter ID. Requires your own ElevenLabs connection.

Tool to update an existing ElevenLabs Conversational AI agent response test by ID. Use when you need to modify test configuration, chat history, success conditions, or other test parameters.

Tool to update the name of a knowledge base document in ElevenLabs Conversational AI. Use when you need to rename an existing knowledge base document.

Tool to update an existing secret in the ElevenLabs ConvAI workspace. Use when you need to modify the name or value of an existing API key, token, or other sensitive value stored in the workspace.

Tool to update Convai settings for the workspace. Use when you need to modify webhook configurations, RAG retention settings, MCP server capabilities, or Livekit stack preferences.

Tool to update Convai dashboard settings for the workspace. Use when you need to configure dashboard charts for monitoring conversational AI performance.

Tool to update an existing conversational AI tool in ElevenLabs workspace. Use when modifying tool settings, descriptions, API endpoints, or behavior configurations. Requires the complete tool_config object with all required fields for the tool type.

Replace an environment variable's values using your own ElevenLabs connection. Null removes an environment's value except production; deleting an environment is a separate operation.

Replace a knowledge-base document's source file. Updates its name, content and metadata, overwriting manual content edits. Requires your own ElevenLabs connection.

Update non-credential settings for an existing MCP server. Requires your own ElevenLabs connection. Credential tokens and custom request headers/metadata are excluded by owner policy; existing auth-connection IDs remain supported.

Update a workspace member identified by email. Only workspace administrators may call this endpoint. Attributes remain unchanged unless specified. Requires your own ElevenLabs connection.

Update a music finetune's name, tags, genre or visibility. Omitted fields are not sent; explicit nulls are sent as null. Requires your own ElevenLabs connection.

Rename an open production order. Requires your own ElevenLabs connection.

Update a Studio project's content from a URL, uploaded document or JSON chapter content. Requires your own ElevenLabs connection; auto_convert can generate audio.

Updates a project's pronunciation dictionaries on ElevenLabs to improve text-to-speech accuracy for specialized terms; note that while multiple dictionaries can be applied, the UI only displays the first.

Partially updates a pronunciation dictionary's metadata (name or archived status) without changing its version. Use when you need to rename or archive/unarchive a dictionary.

Partially update an existing speech engine's connection, ASR, TTS, turn detection, privacy or limits. Omitted fields remain unchanged. Requires your own ElevenLabs connection.

Update a Studio project's name, default voices, and optional download metadata. Requires your own ElevenLabs connection.

Update a conversation tag's title and/or description as its owner or a workspace admin. Omit fields to leave them unchanged. Requires your own ElevenLabs connection.

Rename an existing agent test folder. Currently only the folder name can be updated. Requires your own ElevenLabs connection.

Update configuration overrides for one MCP tool and return its server configuration. Requires your own ElevenLabs connection; omitted settings are not sent and explicit nulls are preserved.

Edit a source transcript segment's text, speaker, or timing (Enterprise only). Omitted fields stay unchanged. Bumps the project revision, discards affected translations in every language target, and marks completed targets stale. Audio changes only when a target is regenerated. Requires your own connection.

Enterprise only: atomically edit source segments' text, speaker, or timing. Increments the transcript revision, discards affected translations in every target language, and marks completed targets stale. Regenerate a target to change its audio. Requires your own ElevenLabs connection.

Edit a dubbing target segment's translation (Enterprise only, own connection). Omitted translation is unchanged; null clears it for re-translation. Increments the target revision and marks a completed target stale. Audio changes only after regenerating the target; source text and other languages remain untouched.

Edit 1–500 segment translations for a dubbing language target atomically (Enterprise only). Increments the target revision and marks completed targets stale. Omitted translations stay unchanged; null requests re-translation. Audio changes only after regenerating the target. Requires your own ElevenLabs connection.

Update a triage ticket's title, description, status, priority, or assignee. Requires viewer access to the ticket's agent and your own ElevenLabs connection. Omitted fields stay unchanged; null clears priority or unassigns the assignee.

Update a voice collection's title and icon, leaving omitted fields unchanged. Requires editor access or higher and your own ElevenLabs connection.

Update a professional voice cloning sample's noise removal, speaker selection, trim times or file name. Requires your own ElevenLabs connection. Speaker selection replaces the previous selection.

Update a WhatsApp account's assigned agent, messaging, audio responses, or typing indicator. Omitted settings are not sent. Requires your own ElevenLabs connection.

Tool to update a specified workspace webhook by its ID. Use when you need to modify webhook settings such as the display name or enable/disable status.

Upload a file as a new asset with a display name and return its metadata and signed content URL. Requires your own ElevenLabs connection.

Upload an image, PDF, or text file for a conversation and return its reference ID. Requires your own ElevenLabs connection.

Upload music for later inpainting and optionally extract a composition plan, timestamps, or waveform. Uploads are charged at song-generation prices and inspected for copyright infringement; detected copyrighted content still incurs half the request cost. Requires your own ElevenLabs connection.

Add or update a dubbing, subtitle, or transcription item on an open production order and return its ID and quoted price. Requires your own ElevenLabs connection.

Submit the user's audio recording to verify a professional voice cloning captcha. Requires your own ElevenLabs connection.

Fetches configurable parameters for ElevenLabs voice generation, used to determine available settings (e.g., accents, character limits) prior to audio synthesis; returns metadata only, not audio.