Integration · Marketing

Connect Claude & ChatGPT to Synthesia

Ask your AI to turn a script into a Synthesia avatar video, or to fill a template with new text. It can check whether a video has finished and get the download link, translate a video into other languages and set up dubbing projects. It can also list your videos and change their title, description or visibility.

Connect Synthesia free

Free plan, no credit card. Takes about a minute.

Try asking

“Make a test welcome video from this script.”
The AI creates a video with a scene that has an avatar, a background and your script. As a test, Synthesia makes a free watermarked version.
“Create a video from our product update template with this week's three points.”
It reads the template's variables and creates a video with your values. Rendering uses your video quota.
“Is the onboarding video done yet?”
It checks the video's status and gives you the download link when it is complete.

What your AI can do

Avatar videos

Create videos from scenes with avatar, background and script, check their status and get the download link when ready.

Templates

List templates, read the variables each one expects and create videos from them with your own values.

Translation and dubbing

Translate videos into supported languages, create dubbing projects from uploaded videos and add target languages.

“Translate the onboarding video into German and Spanish.”
It checks the supported language codes and starts the translation. It can generate the translated videos as private or public.
“Set up dubbing for the uploaded webinar recording in French.”
It creates a dubbing project from the uploaded video asset and can add more target languages later.
“Rename last week's video to 'Q3 kickoff' and make it private.”
It updates the video's title and visibility.

25 tools for Synthesia

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

add_dubbing_languagesChanges dataAdd target languages to a dubbing project (`dubbing_project_id`, `target_languages`).
create_assetChanges dataCreate an upload slot for a media asset (image, video or audio): `content_type` and `configuration`, plus title. Returns details for uploading the file.
create_dubbing_projectChanges dataCreate a dubbing project from an uploaded video asset. Pass the request fields in `body`, such as the asset and target languages.
create_manualChanges dataCreate a new manual. API summary: Translate and generate a video from XLIFF definition.
create_videoChanges dataCreate an AI avatar video from scenes in `input` (each with avatar, background and scriptText), plus title and visibility. Set `test` true for a free watermarked test. Rendering uses your video quota.
create_video_from_templateChanges dataCreate a video from a template: `template_id` and `template_data` with values for the template's variables, plus optional title and visibility. Rendering uses your video quota.
create_webhookDeletesCreate a new webhook. Required: events or url. Destructive action; may require approval. API summary: Create a Webhook.
delete_videoDeletesPermanently delete a video by `video_id`. This cannot be undone.
delete_webhookDeletesPermanently delete a webhook by webhook id. Destructive action; may require approval.
export_audit_logsChanges dataExport audit logs. API summary: Export audit log events as CSV.
get_assetGet one uploaded media asset by `user_media_asset_id`.
get_dubbing_projectGet a dubbing project's status and dubbed videos by `dubbing_project_id`.
get_templateGet one template by `template_id`, including the variables it expects.
get_videoGet one video by `video_id`, including status (in progress or complete) and download link when ready.
get_video_translationsGet the translated versions of a video by `root_video_id`.
get_webhookGet one webhook by webhook id. API summary: Retrieve a webhook.
list_eventsList events. Optional filters: workspace id, organization id, actions, actor ids, target id or start date. Results are paginated. API summary: Query audit log events.
list_templatesList available video templates.
list_translation_languagesList the language codes supported for video translation.
list_video_xliffsList xliffs for a video. Optional filters: video version or xliff version. API summary: Retrieve XLIFF content for a video.
list_videosList your videos, newest first, with paging.
list_webhooksList webhooks. Optional filters: deleted. Results are paginated.
search_eventsChanges dataSearch events. Use this to find existing events before creating a new event. API summary: Search audit log events (Advanced).
translate_videoChanges dataStart translating a video (`root_video_id`) into `target_languages`. Optionally auto-generate the translated videos as private or public.
update_videoChanges dataUpdate a video's title, description, visibility or call-to-action by `video_id`.

Set up in three steps

1
Pick the app
Create a free HeyMyApps account and choose Synthesia from the app list.
2
Paste your key
Paste a Synthesia API key with the Legacy (v2) scope. In Synthesia select Developers in the sidebar, open the API keys tab and click New API key. Choose the Legacy (v2) scope and an expiry, create the key and copy it. It is shown only once.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Synthesia?

It can create videos from scenes or from templates, list and read videos and templates, update a video's title, description, visibility or call to action, and delete videos. It can translate videos, create and extend dubbing projects, and create upload slots for images, video and audio.

Does the AI see my Synthesia API key?

No. Your Synthesia credentials are encrypted at rest and never shown to the AI. After you save them, they are not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start by only reading videos and templates. Rendering a video uses your Synthesia video quota, and deleting a video is permanent. Creating and deleting videos can require your approval before it runs. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your HeyMyApps link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

HeyMyApps has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Synthesia account, and videos you render count against your Synthesia video quota.

Can I try it without using my video quota?

Yes. Ask the AI to create the video as a test. Synthesia then makes a free test video with a watermark. When you are happy with the script and scenes, ask for the real video, which uses your quota.