studio_generate
Generate a piece of content with a Studio format (see studio_formats for the formats, their credit prices and the inputs they need). It spends the credits shown by studio_formats for the chosen duration (and quality, where the format has a Standard and a Premium price): always tell the user the price and get their confirmation first. The script, on-screen text and visuals are written from the brand profile and what you pass (hook, angle, prompt, or the user's own script). Generation runs in the background (seconds for images and text posts, a few minutes for videos and talking heads): this returns a generationId, then call studio_status with it. Results are saved to the media library and can be attached to posts. If the generation fails, the credits are given back. To use one of the user's saved recipes (studio_recipes), pass its recipeId: its format and settings are filled in, what you pass yourself wins. Pass formatId or recipeId. To make a finished generation again ("the same in Premium", "again at 30 s"), pass its id as fromGenerationId with only what changes: its format, words and settings are reused. Made for a post of the user's content plan (the chat names its planItemId): pass planItemId, the result becomes that post's content when it has none yet and is in the post's format (linkedToPlan says whether it did).
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": "studio_generate"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ad | No | Static ads only: the parts the user writes (studio_formats "inputs" says which ones a format needs). | |
| hook | No | A hook formula key from studio_formats, or the hook in the user’s own words | |
| angle | No | The angle or message to push | |
| music | No | Background music of a video, free: "auto" (the default: a library track matched to the post on video clips, slideshows, walls of text and hook + demo; none where a voice speaks), "none", or a library track id (upbeat-1, upbeat-2, upbeat-3, chill-1, chill-2, chill-3, corporate-1, corporate-2, corporate-3, cinematic-1, cinematic-2, cinematic-3, acoustic-1, acoustic-2, acoustic-3, electronic-1, electronic-2, electronic-3, hiphop-1, hiphop-2, hiphop-3, luxury-1, luxury-2, luxury-3, playful-1, playful-2, playful-3, ambient-1, ambient-2, ambient-3). | |
| theme | No | Explainers only: the look of the graphics, "night" (tech, creators, marketing, anything premium or modern), "paper" (editorial: finance, law, health, education, B2B, wellness), "bold" (loud and fun: fitness, food, retail, events, youth brands), "notebook" (teachers and coaches: study tips, how-tos, personal development). Left out, the plan picks one for the brand and avoids the brand's recent ones. | |
| voice | No | A voice by name (studio_options "voices"): who speaks in talking heads, explainers, stories and voiceovers. Left out, the presenter’s own or matched voice. | |
| aspect | No | The frame, where the format offers several (studio_formats "aspects"); left out, the format’s default. | |
| prompt | No | What the content is about, in plain words | |
| script | No | The user’s own script, used word for word | |
| slides | No | Slideshow only: number of slides | |
| effects | No | Talking heads only: animated effects around the presenter (studio_options "effects"): "none" (the default), "auto" (two or three picked for the script) or one effect id. Any choice but none adds its credits. | |
| quality | No | Formats with "qualities" in studio_formats (talking heads, hook + demo, video clip, animated stories): "premium" uses the more realistic video model at its own credit price, "standard" (the default) the cheaper one. Ignored by other formats. | |
| avatarId | No | An avatar id from studio_formats, to keep the same AI creator | |
| captions | No | Burn captions into videos (on by default where the format uses them) | |
| formatId | No | The format id from studio_formats (can be left out when recipeId is given) | |
| language | No | The language the post is written and spoken in (ISO 639-1); left out, the brand’s content language | |
| mediaIds | No | Media library ids: the product image or demo video the format needs; making_of: the 2 to 6 stage photos, in the order of the work | |
| recipeId | No | A saved recipe id from studio_recipes: its format and settings are the defaults, anything else you pass wins | |
| structure | No | Talking heads and voiceovers: how the script is built. "free" (the default) leaves it to the writer, "payoff" holds the hook to one promise the video keeps and ends on one call to action, "reloops" does the same with curiosity loops (short question lines answered right away) inside the payoff. Ignored by other formats and when a script is given. | |
| textStyle | No | Slideshows and walls of text: how on-screen words are drawn ("box_white", "box_black" or "outline"). Left out, the format’s default. | |
| planItemId | No | The content-plan post this is made for: the result is linked to it | |
| durationSec | No | One of the format’s durations | |
| fromGenerationId | No | A generation to make again: its format and inputs are the defaults, anything else you pass wins (leave formatId and recipeId out) |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| error | No | ||
| credits | No | ||
| generationId | No | ||
| linkedToPlan | No | With planItemId: whether the plan post now has this generation as its content |