Create a clip request
clipember_create_clip_requestStart a new AI clipping job from a YouTube (or direct video file) URL. Spends 1 credit — check clipember_get_credit_balance first if unsure. Returns immediately with a requestId; the pipeline (transcribe → score → crop → render) usually takes about 5 minutes, and about 1 run in 10 takes 15+ minutes. Call clipember_get_clip_request to check progress — don't poll more than once every 30-60 seconds, and expect to need a fresh call in a LATER turn/message rather than waiting synchronously in this one.
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": {
"url": "<url>"
},
"name": "clipember_create_clip_request"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| end | No | Seconds into the source to stop (max ~1200 = 20 min window) | |
| url | Yes | YouTube URL or a direct video file URL | |
| genre | No | Genre of the video (auto, qa, commentary, marketing, webinar, motivational, podcast, academic, listicle, product_review, howto, comedy, sports, church, news, vlog, gaming, other) — a hint for the moment picker. | |
| start | No | Seconds into the source to start processing | |
| prompt | No | Which moments to include, in plain words (e.g. 'every moment someone talks about pricing'). | |
| series | No | If true, make a SERIES: one continuous story from the video split into 2-6 consecutive parts, each ending on a cliffhanger, with 'PART n/N' on screen. Schedule them in order with clipember_schedule_series once rendered. | |
| teaser | No | If true, open each clip with a 1-3 second teaser of its payoff line before the clip starts (a cold open). Not applied to series parts. | |
| lengths | No | Clip lengths to look for, several allowed: auto, 0-30s, 30-60s, 60-90s, 90s-3m, 3-5m, 5-10m, 10-15m. Overrides preferredLength. | |
| autoZoom | No | Auto zoom: a short punch-in at the end of sentences. On unless false. | |
| captions | No | false renders the clips without captions. | |
| language | No | Spoken language of the video, ISO 639-1 (e.g. en, uk, es). Default 'auto' detects it from several speech windows across the video; pass it explicitly when the video opens with music or a phrase in another language. | auto |
| watermark | No | Burn a diagonal clipember.com watermark into the rendered clips. Omit to use the account setting (Settings → watermark); pass true/false to override it for this run. | |
| aiKeywords | No | AI keywords: highlight key words in the captions with the style's colors. On unless false. | |
| noClipping | No | If true, render ONE clip of the whole [start,end] range instead of finding multiple highlights | |
| translateTo | No | Caption language: translate the captions into this language (ISO 639-1); the audio stays original. Omit for the spoken language. | |
| autoHeadline | No | Auto headline: a short title from the clip's hook on the first seconds, away from faces. On unless false. | |
| captionStyleId | No | Caption style of the first render: a preset id (karaoke, bold-pop, rise, notebook, marker, …) or the id of a saved style. Omit for the default look. | |
| preferredLength | No | under60sec |