HeyGen MCP server for your AI

Translate a video into one or more target languages.

Translates a video into one or more target languages with voice cloning and lip-sync.

Returns details for a translation job including status, output language, video_url, and failure info if applicable.

List all supported target language codes for video translation.

Check Translation Status

Create a video from a specific avatar or image with full control over avatar, voice, and script.

Creates a video from a HeyGen avatar or an arbitrary image.

Generates a webm video with transparent background and an avatar speaking the input text.

Permanently delete a video.

This API now generates videos with our New AI Studio backend.

This endpoint allows you to retrieve the status and details of a specific video.

Returns details for a video including status, video_url, thumbnail_url, duration, and failure info if applicable.

List videos in the account with pagination and optional filtering.

Registers an HTTPS URL to receive webhook event notifications.

List all avatar groups

List all avatars in one avatar group

Returns a paginated list of avatar looks (outfits, poses, styles).

You can get your Avatars and Talking Photos(Photo Avatars) with this endpoint.

Returns a paginated list of registered webhook endpoints.

Returns all available webhook event types with human-readable descriptions.

Check photo/look generation status

Creates a voice clone from an audio file.

This api can be used to create a photo avatar group For generated photo avatar, pass the generation_id and the image_key For user uploaded avatar, first upload the photo using the upload assets api.

Synthesize speech audio from text using a specified voice.

This endpoint can be used to generate additional looks for a trained photo avatar group.

This endpoint will generate photos that can be used to create photo avatars, returns a generation id, which can be used in the check generation status endpoint to get status and final image/image keys

Get the training status of an avatar group

This endpoint is used to retrieve a list of brand voices your created

List All Voices (V2)

Returns a paginated list of voices, filterable by type, engine, language, and gender.

Synthesize speech audio from text using a specified voice.

Train a photo avatar group.

Create a video from a text prompt using HeyGen's Video Agent.

One-shot video generation from a prompt — agent handles scripting, avatar selection, scene composition, and rendering.

Returns the current status, progress, video_id, and recent chat messages for a session.

Returns all videos produced within a Video Agent session, sorted newest-first.

Begin a direct-to-S3 upload.

Returns metadata for an asset in the caller's workspace — including owner, upload timestamp, file type, and a publicly accessible URL.

Semantically search re-hosted public images and icons by natural-language description, e.g.

Append a text delta to a session created with `type: text_stream`.

Cancel a running streaming session.

Start a low-latency streaming avatar session and return a `stream_id`.

Replaces the audio on an existing video and re-animates the speaker's lip movements to match the new audio.

Get the status of a streaming avatar session.

Returns details for a lipsync job including status, video_url, caption_url, and failure info if applicable.

This API now supports New AI Studio!

This API now supports New AI Studio!

This API now supports New AI Studio!

Checks the current status of the Digital Twin generation process and returns relevant details.

Get Remaining Quota

Returns the authenticated user's profile, remaining credits or balance, and billing details.

Submits the URLs for the required training footage and consent statement to create a Digital Twin.

Creates a proofread session that extracts editable subtitles from a video before final rendering.

Permanently deletes a video translation and its associated files.

Returns presigned download URLs for the edited and original SRT files of a completed proofread session.

Starts final video generation using the approved subtitles from a proofread session.

Returns the status and details of a proofread session.

Get the caption file (SRT or VTT format) for a completed video translation.

Returns all supported target language names for video translation.

Returns a paginated list of all video translation jobs in the account.

Updates the display title of a video translation job.

Replaces the proofread subtitles with an edited SRT file.

Delete a Video

Permanently deletes a video and its associated files.

Get detailed information about a video including status, URLs, and metadata.

This endpoint retrieves a list of videos associated with the user.

Returns a paginated list of all videos in the account.

Add a Webhook Endpoint

Creates a new avatar from an image, video footage, or a text prompt.

Initiates the consent flow for an avatar group and returns a URL for the user to complete approval in their browser.

Permanently deletes an avatar group and all its associated looks.

Deletes an avatar look and its backing resource.

Permanently removes a webhook endpoint.

delete an existing webhook endpoint

Returns details for a specific avatar group including name, gender, preview URLs, looks count, and training status.

Returns details for a specific avatar look including supported engines, preferred orientation, preview URLs, and training status.

Returns a paginated list of avatar groups (characters).

list all your registered webhook endpoints

list all supported webhook events

Returns a paginated history of delivered webhook events.

Generates a new signing secret for a webhook endpoint and immediately invalidates the old one.

Updates the display name of an avatar look.

Updates the URL and/or subscribed event types for a webhook endpoint.

update an existing webhook endpoint

Add other looks to existing photo avatar group

Add motion to an existing photo avatar, returns the id of the new avatar that has motion

This api adds sound effect into a photo avatar

Deletes a voice clone owned by the caller.

Returns up to 3 voices matching a natural language description (e.g.

Returns details for a specific voice, including clone workflow status when available.

List voices available for TTS generation with cursor-based pagination.

Get the details of a photo avatar

Updates an existing brand voice with specified changes.

Call this api to upscale an avatar, can only be called on an avatar that has motion, returns the photo avatar id that is upscaled

Returns a single session resource (image, video, draft, avatar, voice, etc.) by its resource_id.

Returns a paginated list of video agent sessions for the authenticated user, sorted newest-first.

Returns curated visual style templates available for Video Agent sessions.

Sends a follow-up message to an existing session.

Halts an active agent run at its next checkpoint.

This endpoint is used to generate a new access token for a streaming session.

Submit a WebRTC ICE candidate for an Interactive Streaming Avatar session.

This endpoint is used to interrupt the speaking of an Interactive Avatar.

This API endpoint allows you to retrieve a list of public and custom interactive avatars.

This endpoint is used to retrieve a list of currently active streaming sessions.

This endpoint is used to initiate a new streaming session.

This endpoint is used to send a text to an Interactive Avatar, prompting it to speak the provided text.

This endpoint is used to start the connection for an existing streaming session.

This endpoint is used to terminate an active streaming session.

Finalize a direct-to-S3 upload into a reusable asset.

Permanently deletes an asset.

Uploads a file (image, video, audio, or PDF) and returns an asset_id for use in other endpoints.

Uploads a media file (image, video, or audio) to the authenticated user's HeyGen account and returns the asset ID for future use.

Create Folder

Permanently deletes a lipsync job and its associated files.

Retrieves a list of folders with optional filters.

Returns a paginated list of all lipsync jobs in the account.

Restore Folder

Open a Server-Sent Events (`text/event-stream`) stream of per-word timestamps for a session.

Moves a folder to the trash.

Updates the name of an existing folder.

Updates the display title of a lipsync job.

Submit a source video and return a job id immediately.

Submit a video to remove its background.

Submit a multi-workflow graph for asynchronous execution.

Renders a HyperFrames composition (an HTML+JS+assets project bundled as a .zip) into a video.

Submit a single workflow for asynchronous execution.

Soft-deletes an AI clip job and its clips.

Soft-deletes a background removal job.

Soft-deletes a HyperFrames render.

Returns the full job resource including produced clips, statuses, and presigned download URLs.

Returns a background removal job including its status and, once completed, presigned download URLs for the produced layers.

Returns full details for a single HyperFrames render, including status and signed video_url when complete.

Retrieves template details by ID, including variables available for replacement and scene mappings for the New AI Studio.

Poll the status and output of a workflow execution.

Returns a cursor-paginated list of AI clip jobs in the authenticated user's workspace, newest first.

Returns a paginated list of background removal jobs for the account, newest first.

Returns a cursor-paginated list of HyperFrames renders in the account, newest first.

List all available workflow types with their input/output schemas.

Add a contact (one recipient) to a Personalized Video project so an uniquely customized video is rendered for them.

Delete a Talking Photo from your account by its id.

Deletes a Digital Twin by its ID.

Returns the authenticated user's profile, remaining credits or balance, and billing details.

Get the detail/status of a single Personalized Video audience member (one rendered recipient) by its id.

Get the detail of a Personalized Video project by its id — its template variables, settings, and the list/status of audience members (recipients).

List the Talking Photos in your HeyGen account.

Upload a still photo of a face to create a Talking Photo (a photo that can be animated to speak).

List brand glossaries (custom term mappings, a.k.a.

Returns brand kits available in the authenticated user's workspace.

Semantically search the audio catalog by natural-language description — set type=music (the default) for background music (e.g.