Make a video
make_videoDestructive
Make a UGC video of a product. This spends the team's credits: the price quote_video gives for the same choices, refunded if the video fails. Answers an id at once, and with languages an id for each language in ids: call get_video with each about once a minute until its status is ready or failed, which takes a few minutes.
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": {
"product": "<product>",
"credits": "<credits>",
"idempotency_key": "<idempotency_key>"
},
"name": "make_video"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ad | No | An ad to build the video like, its moves made for this product: a link of an ad in the Meta Ad Library, an ad's id from that library or from list_ads, which lists TikTok's ads too, or one of the team's own videos as v- and its id from get_video, with - and its part after for any but its first. A Meta Ad Library link not seen before is looked up in that library and counted against the team's ad links of the day. Not with lines or script_id. | |
| keep | No | What to keep of the ad: structure, the default, or pacing, its pace and its shots alone. | |
| size | No | The shape the video is filmed in. 9:16 is the default. | |
| angle | No | The angle the video argues: auto, the default, or one of the angle ids read_product lists for the product. Not with lines, script_id or ad, which argue their own. | |
| count | No | How many videos to make, each a different take. Not with a script, which is made once for each presenter. | |
| lines | No | Lines for the presenter to say, one a shot: 3 to 5 for a 15-second video, up to 10 for 30 seconds. They are said word for word as sent, not translated, and read by no check of ours. With script_id they replace that script's lines in order. Every person in the ads we make, on camera or heard as a voice, is made by AI and is not a customer. Nothing in an ad may present them as someone who has used the product, because that is a fake testimonial and the law forbids it. So they have no past with it: no time spent with it, no result it has had on their own body, home, pet or life, no before and after of their own, no having bought it, and no job, family role or other identity that makes them sound like a real customer. What they have is the moment: showing the product, using it on camera and reacting to what it does there, saying what it is and what it does, and the facts the product page gives. | |
| photos | No | Photo links from read_product to film the product from. | |
| script | No | Which of its scripts, from 1. 1 by default. | |
| comment | No | For comment_reply alone: the comment the video answers, shown over its first shot. No price, link, email address, @ handle or phone number. | |
| credits | Yes | The credits quote_video gave for these choices; a different figure is refused. | |
| product | Yes | The product's id from read_product, or the product's link. | |
| quality | No | fast, the default, uses Seedance 2.0 mini for trying ideas; best uses Wan 3.0 for the videos the team publishes; priority uses Wan 3.0 Prime, first in our line, at a higher price of its own, refused while it is not offered. seedance25 selects Seedance 2.5 explicitly, independent of the model used by best. Send these quality values, not model names. | |
| seconds | No | The length: fast videos are 15 seconds, best and priority videos 15 or 30 seconds. | |
| captions | No | Captions of what is said, on screen. On by default. | |
| language | No | The language the video is spoken in. Left out, the team's ad language. Arabic, Hungarian and Japanese require quality best or priority. | |
| commenter | No | For comment_reply alone: the name of whoever wrote the comment. No link, email address or phone number. | |
| languages | No | Up to 3 languages to make a script in at once, each its own video at one video's price, the first taking the place of language. Only with script_id, and not with language or lines; a script with words said as typed is made in one language, and the Arabic dialects go together, apart from every other language. Arabic, Hungarian and Japanese require quality best or priority. | |
| placement | No | Where the product is in the video. auto by default. | |
| script_id | No | The id write_scripts answered, to make one of its scripts as a video. | |
| presenters | No | Presenter ids from list_presenters. Left out, one is chosen for the product. | |
| resolution | No | The resolution it is filmed in, a higher one at a higher price: 480p or 720p for fast; 480p, 720p or 1080p for best and priority while 1080p is offered, one not offered being refused with the ones that are. Left out, the one its scripts were written for where script_id names them, else 480p while the team's balance is its free videos, else 720p. An Arabic video whose voice is added after filming is filmed in 720p whatever is asked. quote_video says which. | |
| video_type | No | The kind of video, as the app's Video type, everyday by default: everyday, a plain ad; creator_review, a review filmed to the camera, as people review a product on their own channel; unboxing, the product taken out of a plain box and used for the first time; street_interview, an interviewer heard but not seen hands the person the product; podcast, two people talk at a table until the product comes into it; get_ready, using it is one step of getting ready; tutorial, how it is used, a numbered step a shot; three_things, three things about it, one after another; asmr, slow close shots of the sounds it makes, the person whispering; crush_test, one stress test on camera that harms nobody; giant_product, the product as big as a house in a real place; hidden_camera, filmed as if by a hidden camera, the person talking to themselves; comment_reply, the person answers a comment shown on the video. A type is refused where its placement or language does not suit it, and with lines, ad, angle or script_id, which make the video's shape themselves. | |
| description | No | Describe the video: where it happens, what happens and the point it gets across. Words it gives someone to say, in quotes or not, are said as written and follow the rule given for lines. | |
| video_style | No | casual (the default), professional or energetic. | |
| idempotency_key | Yes | Any string unique to this video. Calling again with the same key and the same arguments answers as the first call did and spends nothing more. | |
| second_presenter | No | For podcast alone: the other person at the table, one of our own presenters by its id from list_presenters, not one the team described. Left out, one is chosen. |