Call posts.add_take
Put a film already recorded onto a story that was waiting for one — 'use this clip for that story', 'attach my recording to this story'. The story stops waiting and its words are written over the film by a drafting run, which is model work charged to the workspace. A story that already has its take is left as it is. Not for trimming the film or changing its look: that is done in Videos, and no verb here does it. Over the API it answers in two calls: without confirmation_id it proposes — says what would happen, returns a confirmation_id and changes, spends and sends nothing; the same arguments again with that confirmation_id, on a member's own API key, do it.
Every result names the workspace it ran in. Say which workspace the answer is about. When the account has more than one workspace and none is selected, this tool refuses with workspace_ambiguous and lists the choices — offer them, never pick one.
Request
- Base URL: https://app.goosybear.ai
- URL: https://app.goosybear.ai/api/v1/tools/posts.add_take
- Auth: HTTP bearer
Headers
Your own id for this request, echoed back and recorded on the audit trail. 1–128 characters from A–Z a–z 0–9 . _ : -, starting with a letter or digit; anything else is replaced by a generated id.
Your key for this write: send the same key when you retry and the first result comes back instead of a second action. Keys are honoured for at least 24 hours. 1–200 visible ASCII characters. Replaces the idempotency_key body field, which still works until 2026-12-31; this action needs a key on one of the two, and the header is the one to send.
Request body
Response
The call was admitted and dispatched. ok says whether the tool succeeded — a refusal the tool itself produced is still a 200, exactly as it is a successful JSON-RPC result over MCP.
Changes
No recorded changes to this operation across all 6 revisions of this API.