Make a faceless video
create_videoUse this for a new faceless video (the style’s pictures, designed screens, captions and sound) from an idea or a script, with no footage. Not for footage (edit_video) or a video already made (apply_document). Send exactly one of idea (Clypmint writes the narration) or script (spoken exactly as supplied), which sets the length, so leave seconds out. Defaults to a 30-second vertical video; seconds 10 to 60. style_id only when they name one or their own fits; every style can make a video from words, in its own look; its inputs are presets: Serif Editorial Launch has inputs.voice:none (no narrator unless the user asks for a voiceover); Bold Navy Statement is narrated, with Chris by default. Optional: sound_effects (on unless false), music_bed (only when true), formats (the main shape first), voice (one of 21 narrators by name), pictures, a song, purpose, instructions. Cost: 3 credits to make, plus 1 for each started minute of voice-over and 1 for each started minute of finished video after the first, plus 2 for each extra format; dry_run: true answers the cost and starts nothing. Answers with studio_url: follow it with check_video. It does not post.
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": {
"operation_id": "<operation_id>"
},
"name": "create_video"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| idea | No | What the video is about, in a line or two: Clypmint writes the narration. | |
| title | No | The video's name in the user's library. | |
| voice | No | The narrator (sarah: calm, health and money; alice: clear British educator; brian: deep documentary; liam: energetic ads). Left out: one that fits. | |
| format | No | The older one-shape switch; formats says more. | vertical |
| script | No | The exact words to narrate, read as written. Send script or idea, not both. | |
| dry_run | No | true: answer the credit cost and start nothing. | |
| formats | No | Every shape to make, the main one first: 9:16, 16:9, 1:1, 4:5. | |
| purpose | No | organic (a post), ad (three openings by default), youtube (horizontal), sales_page. | |
| seconds | No | Any length, 10 to 60. With a script, leave it out: the script sets the length (about 2.5 words a second). | |
| style_id | No | Only one they named or their own (get_profile own_styles). | |
| asset_ids | No | Pictures or clips already in Clypmint to show (src_... from list_assets or save_clip). | |
| music_bed | No | true: lay the style's own music bed under the narration (none unless asked); false: never. music_staging_key brings a song of your own instead. | |
| instructions | No | Anything else the user asked for, in their own words. A link here is not opened: use import_asset. | |
| operation_id | Yes | Same id retries run once. | |
| sound_effects | No | Sound effects: on unless false. | |
| style_version | No | A saved version of the user's own style; its newest when left out. | |
| music_staging_key | No | A song from import_asset (mp3, wav or m4a) to lay under the voice. | |
| asset_staging_keys | No | Pictures the user wants shown (a portrait, a product, an app screen), each imported with import_asset. |
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 |