ElevenLabs

Creates a new chapter either as blank or from a URL.

Creates a new pronunciation dictionary from provided rules.

Adds the given ElevenLab Turbo V2/V2.5 language code to the resource. Does not automatically generate transcripts/translations/audio.

Add approval for a specific MCP tool when using per-tool approval mode.

Create configuration overrides for a specific MCP tool.

Adds a member of your workspace to the specified group. Requires `group_members_manage` permission.

Add rules to the pronunciation dictionary. If a rule with the same string_to_replace already exists, it will be replaced.

Add a shared voice to your collection of voices.

Add a new tool to the available tools in the workspace.

Moves multiple tests or folders from one folder to another.

Assign one or more conversation tags to a conversation. Tags that are already assigned are ignored. Tags must belong to the same workspace.

Finds an AudioNative project matching the provided URL, extracts content from the URL, updates the project content, and queues it for conversion and auto-publishing.

Cancel a running batch call and set all recipients to cancelled status.

Cancel a crawl job and delete all associated documents and folders.

Remove a file upload from a conversation. Only possible if the file hasn't already been used in the conversation.

Compile procedure drafts into a workflow.

Compose a song from a prompt or a composition plan.

Stream a song and its detailed metadata using Server-Sent Events (SSE).

Generate a composition plan from a prompt.

Starts conversion of a specific chapter.

Starts conversion of a Studio project and all of its chapters.

Create a new deployment for an agent

Create a new draft for an agent

Creates a new agent response test.

Create an agent from a config object

Creates a folder for organizing agent tests.

Create a new OAuth2 auth connection for the workspace

Submit a batch call request to schedule calls for multiple recipients.

Create a new branch from a given version of any branch

Creates a new segment in dubbing resource with a start and end time for the speaker in every available language. Does not automatically generate transcripts/translations/audio.

Create a new conversation tag for the workspace.

Create a crawl job to crawl the given URL with specified depth and page limits.

Create a new environment variable for the workspace

Create a folder used for grouping documents together.

Create a new MCP server configuration in the workspace.

Import Phone Number from provider configuration (Twilio, Exotel, or SIP trunk)

Create and auto-convert a podcast project. Currently, the LLM cost is covered by us but you will still be charged for the audio generation. In the future, you will be charged for both the LLM and audio generation costs.

Create a new procedure for the agent on a branch.

Creates a new PVC voice with metadata but no samples

Create a new secret for the workspace

Create a new service account in the workspace. By default, a workspace can have up to 20 service accounts. Enterprise customers may request an increase to this limit, up to 100.

Create a new API key for a service account

Creates a new speaker in a dubbing resource. The speaker is added to every available language and can optionally be associated with an ElevenLabs voice and voice settings.

Create a new Speech Engine resource

Create a knowledge base document containing the provided text.

Create a knowledge base document generated by scraping the given webpage.

Create a voice from previously generated voice preview. This endpoint should be called after you fetched a generated_voice_id using POST /v1/text-to-voice/design or POST /v1/text-to-voice/:voice_id/remix.

Create a new webhook for the workspace with the specified authentication type.

Delete a draft for an agent

Delete an agent

Deletes an agent test folder by ID. Use force=true to delete a non-empty folder and all its contents.

Deletes a specific audio isolation history item and the associated media files.

Delete an auth connection

Permanently delete a batch call and all recipient records. Conversations remain in history.

Deletes a chapter.

Deletes an agent response test by ID.

Delete a particular conversation

Delete a conversation tag. Restricted to the tag owner or a workspace admin.

Deletes a dubbing project.

Delete a music finetune

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

Delete a document or folder from the knowledge base.

Delete a specific MCP server configuration from the workspace.

Delete Phone Number by ID

Delete user's draft for a procedure, resetting to the committed version

Deletes a Studio project.

Delete a sample from a PVC voice.

Delete RAG index for the knowledgebase document.

Removes a sample by its ID.

Delete a workspace secret if it's not in use

Deletes a single segment from the dubbing.

Delete an existing API key for a service account

Delete a Speech Engine resource

Delete a history item by its ID

Delete tool from the workspace.

Delete a previously generated transcript by its ID.

Deletes a voice by its ID.

Delete a WhatsApp account

Delete the specified workspace webhook

Disable the API key used to authenticate this request. Requires the query parameter `api_key_name=self` as an explicit confirmation.

Download one or more history items. If one history item ID is provided, we will return a single audio file. If more than one history item IDs are provided, we will provide the history items packed into a .zip file.

Regenerate the dubs for either the entire resource or the specified segments/languages. Will automatically transcribe and translate any missing transcriptions and translations.

Queue a language target for a project (starts once the project is ready).

Delete a language target.

Full language-target detail.

List a project's language targets (cursor-paginated).

Delete a project and its language targets.

Full project detail, including its language target ids.

List the workspace's dubbing projects (cursor-paginated).

A language target's transcript: source segments with their translations.

Re-dub a target from its edited transcript (charged like a generation).

Edit a segment's translation for a language target.

The project's source transcript, as editable segments.

Add a new source segment to the transcript.

Remove a source segment from the transcript.

Edit a source segment's text, speaker, or timing.

Create a new agent by duplicating an existing one

Updates a chapter.

Updates the specified Studio project by setting the values of the parameters passed.

Edit PVC voice metadata

Update a PVC voice sample - apply noise removal, select speaker, change trim times or file name.

Update an existing API key for a service account

Edit your settings for a specific voice. "similarity_boost" corresponds to "Clarity + Similarity Enhancement" in the web app and "stability" corresponds to "Stability" slider in the web app.

Update the specified workspace webhook

Download all recipients and conversation results for a terminal batch call as CSV.

Compose a song from a prompt or a composition plan.

Returns the number of pages in the agent's knowledge base.

Gets multiple knowledge base document summaries by their IDs.

Get the current link used to share the agent with others

Calculates expected number of LLM tokens needed for the specified agent.

Gets an agent response test by ID.

Gets agent response test summaries for the requested test IDs.

Retrieve config for an agent

Returns summaries for the specified agents.

Gets an agent test folder by ID, including its folder path.

Returns the latest topic discovery run results for a given agent.

Retrieve the widget configuration for an agent

Returns a list of your agents and their metadata.

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

Returns the audio of an history item.

Returns a list of all your audio isolation generations.

Get player settings for the specific project.

Get detailed information about a batch call including all recipients.

Get information about a single agent branch

Returns a list of branches an agent has

Returns information about a specific chapter.

Returns the chapter snapshot.

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

Returns a list of a Studio project's chapters.

Get the audio recording of a particular conversation

Get all conversations of agents that user owns. With option to restrict to a specific agent.

Get the details of a particular conversation

Get a signed url to start a conversation with an agent with an agent that requires authorization

Get SIP messages associated with a conversation's phone call

Get a conversation tag by ID.

Get distinct users from conversations with pagination.

Get details about a specific crawl job including status and progress.

Retrieve Convai dashboard settings for the workspace

Get details about a specific documentation part used by RAG.

Get all RAG chunks for a specific knowledge base document.

Get details about a specific documentation making up the agent's knowledge base

Returns dub as a streamed MP3 or MP4 file. If this dub has been edited using Dubbing Studio you need to use the resource render endpoint as this endpoint only returns the original automatic dub result.

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

Returns transcript for the dub as an SRT or WEBVTT file.

Given a dubbing ID generated from the '/v1/dubbing' endpoint with studio enabled, returns the dubbing resource.

Fetch the transcript for one of the languages in a dub.

Get a specific environment variable by ID

Get a music finetune.

List music finetunes accessible to you (your own, workspace-shared, and ElevenLabs-curated), with optional filtering, sorting, and cursor pagination.

Get all groups in the workspace

Get a list of agents depending on any of the given knowledge base documents.

Get the entire content of a document from the knowledge base

Get a list of agents depending on this knowledge base document

Get a list of available knowledge base documents

Get a signed URL to download the original source file of a file-type document from the knowledge base

Retrieves a list of shared voices.

Get the live count of the ongoing conversations.

Get a WebRTC session token for real-time communication.

Retrieve a specific MCP server configuration from the workspace.

Retrieve configuration overrides for a specific MCP tool.

Gets a list of available models.

Retrieves and/or creates RAG indexes for multiple knowledge base documents in a single request. Maximum 100 items per request.

Retrieve Phone Number details by ID

Get user's draft for a procedure

Retrieve a procedure at a specific version or the current branch HEAD.

Returns information about a specific Studio project. This endpoint returns more detailed information about a project than `GET /v1/studio`.

Returns a list of chapter IDs that have muted tracks in a project.

Returns the project snapshot.

Retrieves a list of snapshots for a Studio project.

Returns a list of your Studio projects with metadata.

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

Get metadata for a pronunciation dictionary

Get a PLS file with a pronunciation dictionary version rules

Returns a list of LLM models and the expected cost for using them based on the provided values.

Retrieve the first 30 seconds of voice sample audio with or without noise removal.

Retrieve the status of the speaker separation process and the list of detected speakers if complete.

Retrieve the visual waveform of a voice sample.

Get captcha for PVC voice verification.

Provides total size and other information of RAG indexes used by knowledgebase documents

Provides information about all RAG indexes of the specified knowledgebase document.

Gets the metadata of a resource by ID.

Get paginated list of resources that depend on a specific secret, filtered by resource type.

Get a workspace secret by ID

Get all workspace secrets for the user

Get all API keys for a service account

Retrieve Convai settings for the workspace

Get a signed url to start a conversation with an agent with an agent that requires authorization

Fetch the top 10 similar voices to a speaker, including the voice IDs, names, descriptions, and, where possible, a sample audio recording.

Generate a time limited single-use token with embedded authentication for frontend clients.

Retrieve the separated audio for a specific speaker.

Retrieve a Speech Engine resource

Returns a list of your generated audio (e.g. text to speech, speech to speech, Studio, dubbing). Music and SFX generations are not included and cannot currently be retrieved via the API.

Retrieves a history item.

Gets a test invocation by ID.

Get a list of agents depending on this tool

Get paginated list of tool executions for a specific tool.

Get tool that is available in the workspace.

Get all available tools in the workspace.

Retrieve a previously generated transcript by its ID.

Gets information about the user

Gets extended information about the users subscription

Gets a list of all available voices for a user with search, filtering and pagination.

Get metadata for a specific agent version

Gets the list of available accents in the shared voice library.

Returns metadata about a specific voice.

Returns the settings for a specific voice. "similarity_boost" corresponds to"Clarity + Similarity Enhancement" in the web app and "stability" corresponds to "Stability" slider in the web app.

Gets the default settings for voices. "similarity_boost" corresponds to"Clarity + Similarity Enhancement" in the web app and "stability" corresponds to "Stability" slider in the web app.

Returns a list of all available voices for a user. Stops working once the user's workspace exceeds 500 voices.

Get a WhatsApp account

Returns the audit log for the workspace. Requires enterprise tier and the audit_log_read permission.

Get all batch calls for the current workspace.

Gets a list of all members of the workspace, including locked members. Service accounts are excluded. Requires the workspace_members_read permission.

List all service accounts in the workspace

List all webhooks for a workspace

Handle an outbound call via Exotel Connect API

Handle an outbound call via SIP trunk

Handle an outbound call via Twilio

Sends an email invitation to join your workspace to the provided email. If the user doesn't have an account they will be prompted to create one. If the user accepts this invite they will be added as a user to your workspace and your subscription using one of your seats. This endpoint may only be called by workspace members with the WORKSPACE_MEMBERS_INVITE permission. If the user is already in the workspace a 400 error will be returned.

Sends email invitations to join your workspace to the provided emails. Requires all email addresses to be part of a verified domain. If the users don't have an account they will be prompted to create one. If the users accept these invites they will be added as users to your workspace and your subscription using one of your seats. This endpoint may only be called by workspace members with the WORKSPACE_MEMBERS_INVITE permission.

Get all auth connections for the workspace

Returns a list of available LLM models that can be used with agents, including their capabilities and any deprecation status. The response is filtered based on the data residency of the deployment and any compliance requirements (e.g. HIPAA) of the workspace subscription.

Lists all agent response tests with pagination support and optional search filtering.

List conversation tags for the workspace, ordered by most recently created first.

Get a list of ongoing and recent crawl jobs for the user.

List the dubs you have access to.

List all environment variables for the workspace with optional filtering

Retrieve all tools available for a specific MCP server configuration.

Retrieve all MCP server configurations available in the workspace.

Retrieve all Phone Numbers

List the agent's procedures on a branch with their procedure_id, version_id, name, type, trigger, and has_draft. has_draft is true when a procedure has unpublished draft changes on this branch; its name/type/trigger then reflect that draft. Does not return procedure content -- use Get Procedure to read a procedure's body.

Get SIP messages for a phone number

Returns a paginated list of Speech Engine resources.

Lists all test invocations with pagination support and optional search filtering.

List all WhatsApp accounts

Merge a branch into a target branch

Returns the result of merging the source branch into the target branch without performing the merge. Useful for showing an accurate diff before confirming.

Change the attribution of one or more segments to a different speaker.

Patches an Agent settings

Partially update the pronunciation dictionary without changing the version

Send the feedback for the given conversation

Delete multiple documents or folders from the knowledge base. Each id succeeds or fails independently.

Moves multiple entities from one folder to another.

Moves the entity from one folder to another.

Creates a new Productions order in the workspace. The order starts in the open state and can be configured with items before submission.

Returns the available languages for a given order item kind.

Retrieves metadata and a time-limited download URL for a previously uploaded media file.

Retrieves full details for a Productions order. Quote and pricing information may not be available immediately; if you wish to see the quote before submission, you may need to poll the order details until it is ready.

Retrieves the delivered files for a completed order. Returns an empty list if the order is not yet completed.

Lists Productions orders in the workspace. Supports filtering by status and date range, with pagination.

Removes an order item from an open order.

Submits an open order for processing. The order must have at least one item. Once submitted, items can no longer be modified. Upon submission, the workspace will be charged for the order. The quote is based on information extracted from the uploaded media, such as its duration. The quote may not be available immediately; if you wish to see the quote before submission, you may need to poll the order details until the quote is ready.

Updates an open order.

Adds or updates an order item on an open order. Returns the item ID and the quoted price.

Run the agent's exact RAG retrieval for an ad-hoc query and return the ranked chunks the agent would retrieve. Read-only: no conversation is created. The response reflects current retrieval internals and may evolve.

In case the document is not RAG indexed, it triggers rag indexing task, otherwise it just returns the current status.

Rebase a branch onto the latest main branch, incorporating main's changes while preserving the branch's own changes.

Returns the result of rebasing the branch onto main without performing the rebase. Useful for showing an accurate diff before confirming.

Redirect To Mintlify

Manually refresh a URL document by re-fetching its content from the source URL.

Register a Twilio call and return TwiML to connect the call

Remove approval for a specific MCP tool when using per-tool approval mode.

Remove configuration overrides for a specific MCP tool.

Removes a member from the specified group. Requires `group_members_manage` permission.

Remove a procedure from the agent's draft working set.

Remove rules from the pronunciation dictionary

Regenerate the output media for a language using the latest Studio state. Please ensure all segments have been dubbed before rendering, otherwise they will be omitted. Renders are generated asynchronously, and to check the status of all renders please use the 'Get Dubbing Resource' endpoint.

Returns a list of API requests. Supports filtering by time range, column filters, and search terms. At least one of start_time or end_time must be provided. An optional sort parameter controls timestamp ordering. Results are ordered by timestamp. Descending if end_time is used, ascending if start_time is used. The response is a tabular structure with columns, column_types, column_units, and rows.

Resolve a conversation URL (a Slack message URL or a Zendesk ticket URL) to the deterministic conversation ID for the given agent, then confirm the conversation exists.

Resubmits specific test runs from a test invocation.

Retry a batch call, calling failed and no-response recipients again.

Run selected tests on the agent with provided configuration. If the agent configuration is provided, it will be used to override default agent configuration.

Run the analysis for a conversation using the agent's current evaluation criteria and data collection settings.

Rerun a specific evaluation for a conversation.

Deprecated. Use the `/v1/convai/agent-testing/create` and `/v1/convai/agents/:agent_id/run-tests` endpoints to create and run simulations. Run a conversation between the agent and a simulated user.

Deprecated. Use the `/v1/convai/agent-testing/create` and `/v1/convai/agents/:agent_id/run-tests` endpoints to create and run simulations. Run a conversation between the agent and a simulated user and stream back the response. Response is streamed back as partial lists of messages that should be concatenated and once the conversation has complete a single final message with the conversation analysis will be sent.

Start PVC training process for a voice.

Searches for user groups in the workspace. Multiple or no groups may be returned.

Fuzzy text search over knowledge base document content

Replaces all existing rules on the pronunciation dictionary with the provided ones.

Set the workspace-wide Third-Party Disabling policy. When set, it forces, for every API key in the workspace, whether the holder of a key (potentially a third party who found it) may disable it via the self-disable endpoint or when it leaks publicly — overriding each key's own setting. Pass `true` to allow it for all keys, `false` to forbid it for all keys, or `null` to clear the override so per-key values and the plan default apply again. Workspace admins only.

Grants a role (one of 'admin', 'editor', 'commenter', or 'viewer') on a workspace resource to a user, group, or workspace (service account) API key. This overrides any existing role the target has on the resource. To target a user or service account, pass only the user email; the user must be in your workspace. To target a group, pass only the group id. To target a workspace (service account) API key, pass the api key id; the resource will be shared with the service account associated with that key. You must have admin access to the resource to share it.

Search conversation transcripts by semantic similarity to surface relevant messages based on meaning and intent, rather than exact keyword matches

Turn text into sound effects for your videos, voice-overs or video games using the most advanced sound effects models in the world.

Start speaker separation process for a sample

Stream the audio from a chapter snapshot. Use `GET /v1/studio/projects/{project_id}/chapters/{chapter_id}/snapshots` to return the snapshots of a chapter.

Stream a composed song from a prompt or a composition plan.

Returns a compressed archive of the Studio project's audio.

Stream the audio from a Studio project snapshot.

Search through conversation transcript messages by full-text and fuzzy search

Converts a list of text and voice ID pairs into speech (dialogue) and returns audio.

Generate dialogue from text with precise character-level timing information for audio-text synchronization.

Converts a list of text and voice ID pairs into speech (dialogue) and returns an audio stream.

Converts a list of text and voice ID pairs into speech (dialogue) and returns a stream of JSON blobs containing audio as a base64 encoded string and timestamps

Converts text into speech using a voice of your choice and returns audio.

Generate speech from text with precise character-level timing information for audio-text synchronization.

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

Converts text into speech using a voice of your choice and returns a stream of JSONs containing audio as a base64 encoded string together with information on when which character was spoken.

**Deprecated.** Use `POST /v1/text-to-voice/design` instead. Generate a custom voice based on voice description. This method returns a list of voice previews. Each preview has a generated_voice_id and a sample of the voice as base64 encoded mp3 audio. To create the voice use `POST /v1/text-to-voice` with the chosen `generated_voice_id`.

Design a voice via a prompt. This method returns a list of voice previews. Each preview has a generated_voice_id and a sample of the voice as base64 encoded mp3 audio. To create a voice use the generated_voice_id of the preferred preview with the /v1/text-to-voice endpoint.

Stream a voice preview that was created via the /v1/text-to-voice/design endpoint.

Remix an existing voice via a prompt. This method returns a list of voice previews. Each preview has a generated_voice_id and a sample of the voice as base64 encoded mp3 audio. To create a voice use the generated_voice_id of the preferred preview with the /v1/text-to-voice endpoint.

Regenerate the transcriptions for the specified segments. Does not automatically regenerate translations or dubs.

Regenerate the translations for either the entire resource or the specified segments/languages. Will automatically transcribe missing transcriptions. Will not automatically regenerate the dubs.

Remove a single conversation tag from a conversation.

Removes any existing role on a workspace resource from a user, group, or workspace (service account) API key. To target a user or service account, pass only the user email; the user must be in your workspace. To target a group, pass only the group id. To target a workspace (service account) API key, pass the api key id; the resource will be unshared from the service account associated with that key. You must have admin access to the resource to unshare it. You cannot remove permissions from the user who created the resource.

Updates an agent response test by ID.

Updates an agent test folder. Currently only supports updating the folder name.

Update an auth connection

Update agent branch properties such as archiving status and protection level

Update a conversation tag's title and/or description. Restricted to the tag owner or a workspace admin.

Update Convai dashboard settings for the workspace

Update the name and/or content of a document.

Replace an environment variable's values. Use null to remove an environment (except production).

Update a music finetune.

Update the approval policy configuration for an MCP server. DEPRECATED: Use PATCH /mcp-servers/{id} endpoint instead.

Update the configuration settings for an MCP server.

Update configuration overrides for a specific MCP tool.

Update assigned agent of a phone number

Create or update user's draft for a procedure

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

Update an existing secret for the workspace

Modifies a single segment with new text and/or start/end times. Will update the values for only a specific language of a segment. Does not automatically regenerate the dub.

Update Convai settings for the workspace

Amend the metadata associated with a speaker, such as their voice. Both voice cloning and using voices from the ElevenLabs library are supported.

Update a Speech Engine resource (partial update)

Update tool that is available in the workspace.

Update a WhatsApp account

Updates attributes of a workspace member. Apart from the email identifier, all parameters will remain unchanged unless specified. This endpoint may only be called by workspace administrators.

Returns credit usage broken down by product type over time. The response is a tabular structure with columns, column_types, column_units, and rows.

(Deprecated) This endpoint is deprecated. Use /v1/workspace/analytics/query/usage-by-product-over-time instead, which exposes the bucket size as `interval_seconds` (an integer in seconds) rather than `aggregation_interval`. Returns the usage metrics for the current user or the entire workspace they are part of. The response provides a time axis based on the specified aggregation interval (default: day), with usage values for each interval along that axis. Usage is broken down by the selected breakdown type. For example, breakdown type "voice" will return the usage of each voice for each interval along the time axis.

Make an outbound call via WhatsApp

Send an outbound message via WhatsApp