Edit a video
edit_videoEdits footage into a finished video. Use this when the user has footage to edit: a montage, a talking edit, a long recording cut into clips, an ad with hooks. Not for a video from an idea or script (create_video) or one already made (apply_document). Each detail has its own field; instructions holds anything else, word for word. Clypmint watches the footage itself. In ChatGPT the video is attached as video; elsewhere the answer carries a private upload link good for 2 hours, and editing starts when the file lands. One upload per video. Cost: 3 credits to make, plus 1 for each started minute of footage and 1 for each started minute of finished video after the first, plus 2 for each extra hook, length or format and 2 for each clip; dry_run: true answers the cost and starts nothing.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "edit_video"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | talking: their words lead (talking head, interview, podcast). montage: pictures and music lead (sport, travel, b-roll). Left out, Clypmint decides from the footage. | |
| clips | No | Clips alone from one recording (no main film): podcasts, streams, long talks. | |
| hooks | No | Openings to make (1-3): an ad gets 3 by default, the main cut counting as one. | |
| names | No | Exact person, company and product names to spell right in this video. | |
| title | No | The video's name in the user's library. | |
| video | No | The video the user attached in ChatGPT: always pass it here, never an upload script. Leave out only when nothing is attached, to get a private upload link. | |
| length | No | Finished length: "45-60 s" is {min_seconds: 45, max_seconds: 60}; "under a minute" is {max_seconds: 60}. Leave out if none named. | |
| shorts | No | Shorts to cut from the recording too (0-10), or 'all' the good ones. | |
| dry_run | No | true: answer the credit cost and start nothing. | |
| formats | No | Only when the user asked for a shape: 9:16 (vertical, TikTok, Reels, Shorts), 1:1 (square), 4:5, 16:9 (YouTube, widescreen), the main one first. Left out, nothing is cropped. | |
| purpose | No | organic (a post), ad (three openings by default), youtube (horizontal), sales_page. | |
| style_id | No | Only one they named or their own (get_profile own_styles). | |
| asset_ids | No | Pictures or clips already in Clypmint to use (src_... from list_assets or save_clip). | |
| spellings | No | Heard-to-correct spellings for this video, e.g. {"KMAC":"KMAK"}. | |
| source_url | No | A public https link to the footage (where links are open), instead of a file. | |
| song_upload | No | true when the user has a song file but no link: the upload link then takes the video and the song together. Leave out with music_staging_key. | |
| camera_sound | No | The footage's own sound. mute: only the song plays (the default for a montage with a song). keep: the camera sound stays (the default otherwise). | |
| footage_from | No | A video_id already made from this footage: a new edit of it with no new upload (another kind, length or style). | |
| instructions | No | Anything else the user asked for, in their own words, usually a sentence or two; not what has its own field. Never describe the footage or write rules. | |
| operation_id | No | Same id retries run once. | |
| speaker_name | No | Who is talking, spelled right, e.g. "Dr. Ana Ruiz". | |
| reference_url | No | Saves this public Instagram, TikTok, X, Facebook, Loom or LinkedIn video's captions and pacing as a style; no style_id. Its edit: get_guide references. | |
| sound_effects | No | true: sound effects on the edit. | |
| style_version | No | A saved version of the user's own style; its newest when left out. | |
| reference_mode | No | clone (default): measured closely; slower, a monthly style copy, then credits. match: fast, approximate, included. | |
| speaker_company | No | The speaker's company or business, spelled exactly for this video. | |
| music_staging_key | No | The song for this video, from import_asset (mp3, wav or m4a): a montage's soundtrack, or music under the speech. | |
| asset_staging_keys | No | Pictures from import_asset to use, such as a logo (stg_...). |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| code | No | ||
| cost | No | ||
| error | No | ||
| state | No | ||
| status | No | ||
| dry_run | No | ||
| message | No | ||
| plan_id | No | ||
| style_id | No | ||
| video_id | No | ||
| available | No | ||
| import_id | No | ||
| output_id | No | ||
| studio_url | No | ||
| version_id | No |