Add a still image to a long video
add_stillPuts a still image over a long-form project while the voice carries on, pinned to the transcript: it appears as the word at is said and goes with until, by default at the end of its sentence (8 s at most; 20 s with until). at_seconds and until_seconds take moments in the finished video instead and are turned into words once. placement: full (default, covers everything), screen (the screen's box, the camera bubble stays on top), inset (a rounded box in a corner) or split (the frame halved, the camera on one side and the image on the other; the screen recording isn't shown). It pushes in slowly and fades by default (an inset holds still). The image is asset_id from the brand kit, image_url (a ClipLaunch image link or a public https image the person gave you or owns), image_file (ChatGPT only: the image the person attached) or upload: true, for the person's own picture that is not on ClipLaunch yet: the still waits, and the reply has upload_url to give them and upload_post_url for your code sandbox (one image, valid an hour). PNG, JPEG or WebP, up to 20 MB, at least 480 pixels on its shorter side. Free. Returns still_id, status (ready, hidden with the reason, or needs_upload), start_seconds and end_seconds, the words it is pinned to, how the image fits and what to do next.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"project_id": "<project_id>"
},
"name": "add_still"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| at | No | The word it appears on, { take_id, word } from get_transcript | |
| fit | No | auto (default) fills its box when that keeps three quarters of the image, else shows it whole over a blurred copy; fill crops; whole shows all of it | |
| fade | No | Seconds of fade in and out: 0 for a cut, or 0.1 to 0.5; default 0.3. A split doesn't fade | |
| move | No | in (a slow push from 100% to 110%), out, or none; default in, none for an inset | |
| side | No | placement split only: the half the still takes; default left | |
| focus | No | The point of the image to push towards and crop around, 0 to 1 each way; default the centre | |
| inset | No | placement inset only: its corner and width (0.2 to 0.5 of the frame); default a corner clear of the presenter, 0.35 | |
| until | No | The word it goes with; leave out (or null) for the default: the end of its sentence, at most 8 s | |
| upload | No | true: the person gives their own picture. The still is saved waiting, and you get upload_url for them (valid an hour). false is the same as leaving it out | |
| asset_id | No | An image in the brand kit (get_brand lists its asset ids): the project's kit, or brand_id's | |
| brand_id | No | The kit asset_id is in; default the project's | |
| image_url | No | A ClipLaunch image link (a generate_assets stored_url, a compose_asset URL, a get_brand view_url), or a public https image the person gave you or owns. Fetched once, now | |
| placement | No | full (default) covers the frame; screen fills the screen's box under the camera bubble; inset is a rounded 16:9 box in a corner; split halves the frame, the camera on one side and the still on the other (the screen recording isn't shown) | |
| at_seconds | No | Or the moment in the finished video (what review_render shows), turned into the word playing then | |
| image_file | No | ChatGPT only: the image the person attached, as a list of one. Leave out in other apps | |
| project_id | Yes | From create_project | |
| until_seconds | No | Or the moment in the finished video it goes, turned into the last word started by then |