approve_render
ChatGPTApprove a finished render, as the workspace owner would. Only for connections the owner has allowed to approve.
approve_slides
ChatGPTApprove a Video's stills as its Slides, as the workspace owner would: a PDF with one page per still, and the stills as PNGs, with a receipt. The latest revision unless you name one; its stills must have been made. Only for connections the owner has allowed to approve.
cancel_render
ChatGPTStop a render that has not finished. A finished render cannot be cancelled.
create_cut
ChatGPTCreate a named Video holding the composition as revision 1, in an existing Campaign (campaignId, from get_creation_options) or a new one (campaignName). The Campaign's name also becomes a pin on the new video. Refused with diagnostics when the composition or a pin name has errors. The same as create_video, under its earlier name.
create_video
ChatGPTCreate a named Video holding the composition as revision 1, in an existing Campaign (campaignId, from get_creation_options) or a new one (campaignName). The Campaign's name also becomes a pin on the new video. Refused with diagnostics when the composition or a pin name has errors.
get_component
ChatGPTA library component's full definition (description, props and render tree), from this workspace's Library or the bundled one. Read it before using a component; copy it into the composition's components.
get_creation_options
ChatGPTStart here. The node and property lists, easings, transitions, the font catalogue, this workspace's assets, Campaigns, videos and pins, the component library by name with each component's props, the names of the templates and the schema parts. get_example, get_component and get_schema return the full documents one at a time.
get_cut
ChatGPTA Video's composition at a revision, with who saved it and when, and every note on the video, newest first. An open note, on the latest revision, is the person asking for a change. The same as get_video, under its earlier name.
get_cut_stills
ChatGPTA Video's stills: one at the middle of each narration line and each silent scene, rendered in Chromium, each with its layout warnings: text_overflow, off_canvas, overlap, low_contrast. Sixty requests an hour per workspace. The same as get_video_stills, under its earlier name.
get_example
ChatGPTOne template, a complete composition to start from, by name: product-launch, hold-across-lines, loop, slides (silent, no narrator), steps-coach, numbers-real-estate or question-clinic.
get_image_request
ChatGPTCheck the exact photos from request_images after the person says done. Returns waiting, ready or expired, with the received image ids, names and dimensions. Use the returned ids in Img nodes; validate and save a new Video revision and check Stills. Do not assume the most recently added workspace image belongs to this conversation.
get_join
ChatGPTA join's state (queued, joining, ready, failed or deleted) and its chapters, each with where it starts and, when its video has a newer approved render, newerApprovedRender. Once ready: links to the MP4, captions and transcript, valid for fifteen minutes. Without joinId: the joins the Project keeps and its two newest failed ones, newest first.
get_render_result
ChatGPTA finished render: links to the video and line stills valid for fifteen minutes, captions, transcript and receipt.
get_render_status
ChatGPTWhere a render is: queued, tts, frames, mux, ready or failed. While queued it is waiting for a free render slot, and estimatedWaitSeconds says about how long. Check again gently, about once a minute; the render starts by itself.
get_schema
ChatGPTThe composition JSON Schema, one part at a time. Without part: the document-level schema with each definition marked by the part that holds it, and the list of parts. With part (for example style, animation or node:Sequence): those definitions in full. Use it when a diagnostic needs the exact shape.
get_slides
ChatGPTA Video's approved Slides: links to the PDF and each still as a PNG, valid for fifteen minutes, and the receipt. The latest approved revision unless you name one.
get_video
ChatGPTA Video's composition at a revision, with who saved it and when, and every note on the video, newest first. An open note, on the latest revision, is the person asking for a change.
get_video_quote
ChatGPTThe maximum AI credits for new narration, reused lines and estimated Video minutes for a saved revision, and under minutes the workspace's Video minutes as whoami reports them with this revision's estimatedMs and fits: whether render_video would find enough minutes for it now (false means it would answer credits_exhausted). Show this to the person before rendering. A quote for a Video with nothing to narrate costs nothing and does not expire while the Video is unchanged; a quote with narration to generate lasts fifteen minutes. Spending above the owner’s cap requires their confirmation in Studio; this tool cannot confirm it.
get_video_stills
ChatGPTA Video's stills: one at the middle of each narration line and each silent scene, rendered in Chromium, each with its layout warnings: text_overflow, off_canvas, overlap, low_contrast. Sixty requests an hour per workspace.
join_videos
ChatGPTJoin a Project's approved videos, in playing order, into one MP4 with stitched captions and a transcript. The approved renders are copied, not rendered again, so a join uses no minutes. Chapters must share a size, frame rate, narrator and language; a chapter with no narration fits any. A join holds 2 to 12 chapters and at most 60:00; a Project keeps at most 3 joins, and one join runs at a time in a workspace. A join never changes: to include a fixed chapter, approve its new render and join again. Call get_join for the file.
list_images
ChatGPTFind up to 200 recent workspace images to reuse, including names such as Logo from earlier photo requests. If names match more than one image, ask the person which one. Reuse the exact returned id in the Composition.
list_render_jobs
ChatGPTThe workspace's twenty most recent renders.
move_video
ChatGPTMove a Video to another Project, where the wall groups it: to.campaignId for an existing Project (get_creation_options lists them), or to.campaignName for one by name (the Project with that name, else a new one). The video keeps its id, revisions, renders, stills, pins, notes and files; a campaignId you hold from before still finds it, and the answer carries the new one. Nothing happens for the Project it is already in.
patch_video
ChatGPTSave the next revision of a Video by applying a list of edits to the revision you read, instead of sending the whole composition. Prefer it to update_video for small changes to a revision you have read; send update_video for a rewrite. ops is a list of { op, path, value }: replace, add, remove and test, as in JSON Patch (RFC 6902). path is a JSON Pointer into the composition document (RFC 6901), for example /children/2/children/0/props/x or /title; list positions are numbers, add with "-" at the end of a list appends, and "~1" stands for "/" in a name. test checks a value before the edits that follow it. Edits apply in order to a copy of the revision. If any edit fails (a path that is not there, a failed test) or the result has errors, nothing is saved and the answer names the operation and its path, or gives the same diagnostics as update_video. At most 200 operations and 64 KB. expectedRevision is the revision you read; if someone saved since, the save is refused and nothing changes. Pass withStills: true to get the stills' layout warnings back with the save, instead of calling get_video_stills; a long list of warnings is cut to the first 10 per still, with warningCounts for all.
publish_component
ChatGPTPublish a component definition to the workspace Library as the next version of its name. Published versions never change.
register_asset
ChatGPTAdd an image (PNG, JPEG, WebP) or audio file (WAV, MP3) to the workspace under an id that compositions name. Send files up to 2 MB as bytesBase64; for larger files omit bytesBase64 and PUT the file to the upload URL returned. Asset ids never change meaning.
render_cut
ChatGPTRender a Video's revision to a finished video: narration for each line, then capture and encode. Uses the workspace's minutes and emails the owner when it finishes. Poll get_render_status until done. The same as render_video, under its earlier name.
render_video
ChatGPTRender a Video's revision to a finished video: narration for each line, then capture and encode. Uses the workspace's minutes and emails the owner when it finishes. Poll get_render_status until done.
request_images
ChatGPTAsk the person for one to six named photos. Returns a Fablyn page where they sign in and add the photos, and reserved image ids for clients that can transfer bytes directly. Give them the link; after they say done, call get_image_request. The link lasts 24 hours and does not grant account access. No Video is changed.
update_cut
ChatGPTSave the next revision of a Video. expectedRevision is the revision you read; if someone saved since, the save is refused and nothing changes. The same as update_video, under its earlier name.
update_video
ChatGPTSave the next revision of a Video. expectedRevision is the revision you read; if someone saved since, the save is refused and nothing changes.
validate_cut
ChatGPTValidate a video's composition without saving it: every error with the path in the document (and in the component definition, when inside one), and the timeline at the estimated speaking rate. Validation failures are recorded to help improve diagnostics. The same as validate_video, under its earlier name.
validate_video
ChatGPTValidate a video's composition without saving it: every error with the path in the document (and in the component definition, when inside one), and the timeline at the estimated speaking rate. Validation failures are recorded to help improve diagnostics.
whoami
ChatGPTThe account email and user ID, workspace name and ID, Connected agent and current Grant permissions for this MCP connection. Use this to answer who is connected or where a Video will be created; the account open in Studio may differ. Also the workspace's Video minutes: funding is what the next render uses (paid, welcome, none, or unmetered while minutes are not checked), with remainingMs of it, paidRemainingMs and welcomeRemainingMs. Welcome minutes are used by every finished render, approved or not; paid minutes by each approved Video, and a paid render needs at least a minute left. Requires no write, narration, render or approve permission.