revid-script-with-custom-media
Render a video from a script using only the media assets the caller provides (no stock visuals). Use for branded content where every frame must be on-brand — product clips, brand b-roll, hand-shot footage. Calls the Revid MCP server (render_video → get_project_status).
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- revid-script-with-custom-media
- metadata
- { "openclaw": { "requires": { "config": [ "REVID_API_KEY" ] } } }
- description
- Render a video from a script using only the media assets the caller provides (no stock visuals). Use for branded content where every frame must be on-brand — product clips, brand b-roll, hand-shot footage. Calls the Revid MCP server (render_video → get_project_status).
02 资源文件 2
- 参考文档examples/branded-script.json1.2 KB
- 脚本examples/run.sh740 B
03 SKILL.md 正文
Script + your own media → branded video
Calls the Revid MCP server (
https://www.revid.ai/api/mcp). Install once — seerevid-api-foundations.
For when the user has the script and the visuals. Revid only handles voice + captions + assembly. No stock content is mixed in.
When to use this skill
- The user has both a script and a set of clips/images they want used.
- Brand fidelity matters more than visual variety.
- For mixed (your media + stock to fill gaps), drop
media.useOnlyProvidedand userevid-script-to-videowithmedia.provided.
Inputs
| Field | Required | Notes |
|---|---|---|
text |
yes | The script |
media.provided[] |
yes | At least 3 items recommended; URLs must be public |
aspectRatio |
no | Default 9:16 |
voiceId |
no | Default voice if omitted |
MediaItem shape:
{ "url": "https://…", "type": "image" | "video" | "audio", "title": "optional", "noReencode": false }
Use type: "image" for stills (Revid will optionally pan/zoom them via
media.turnImagesIntoVideos). Use type: "video" for clips. Keep clip
duration roughly comparable to the script length.
Step-by-step
- Validate every
media.provided[].urlreturns 200 and a video/image content-type. - Confirm enough assets for the script: rough rule = 1 asset per 8–10 s of script, minimum 3.
- Call MCP tool
render_videowith the payload below (notemedia.useOnlyProvided: true) — returnsdata.pid. Then poll MCP toolget_project_statuswith thatpidevery 5–8 s untildata.status === "ready". Optionally callexport_videofor a freshly named mp4.
render_video arguments
{
"workflow": "script-to-video",
"source": {
"text": "{SCRIPT}"
},
"aspectRatio": "9:16",
"voice": { "enabled": true, "voiceId": "aria-en-us", "stability": 0.6, "speed": 1.0 },
"captions": { "enabled": true, "position": "middle", "autoCrop": true },
"music": { "enabled": true, "syncWith": "beats" },
"media": {
"type": "custom",
"useOnlyProvided": true,
"turnImagesIntoVideos": true,
"mergeVideos": false,
"animation": "soft",
"provided": [
{ "url": "https://cdn.example.com/clip-1.mp4", "type": "video" },
{ "url": "https://cdn.example.com/clip-2.mp4", "type": "video" },
{ "url": "https://cdn.example.com/hero.jpg", "type": "image" }
]
},
"options": {
"summarizationPreference": "no-summarization",
"useOnlyProvidedMedia": true,
"soundEffects": false,
"hasToGenerateCover": true
},
"render": { "resolution": "1080p", "frameRate": 30 }
}
Both media.useOnlyProvided and options.useOnlyProvidedMedia should be
true — they belong to slightly different paths in the legacy code and setting
both is the safest way to forbid stock fill.
Polling
Call get_project_status with the pid returned by render_video. Stop when
data.status === "ready"; fail when data.status === "failed". Cadence:
5 s, then 8 s once progress > 30. Full pseudocode:
revid-api-foundations § Polling.
Examples
examples/branded-script.json— copy-paste body forrender_video(also a valid POST body for the direct HTTPS fallback).examples/run.sh— bash smoke test using the direct HTTPS fallback (POST /api/public/v3/render→GET /status). Useful when you don't have an MCP client at hand.
Failure modes
| Symptom | Fix |
|---|---|
| Final video pads with stock anyway | One of the two flags wasn't honored. Make sure both media.useOnlyProvided: true AND options.useOnlyProvidedMedia: true are set. |
| Video too short / dead air | Not enough assets. Add more provided items or set mergeVideos: true to loop the existing clips. |
| Wrong asset on a particular line | Pre-order assets in the array roughly in narrative order — Revid uses array order as a hint. |
| Asset URL 403 / 404 | Make sure assets are public (signed URLs work as long as they don't expire mid-render). |
ok: false, error: "insufficient_credits" |
Drop media.quality to "standard" or render.resolution to "720p", or call buy_credit_pack. |
See also
revid-script-to-videofor stock visuals.revid-shopify-product-promofor the product-page variant.
04 同仓库更多 Skills
worktable-review-with-annotations
Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.
worktable-find-and-synthesize-context
Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.
worktable-create-or-update-docs
Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.
worktable-create-or-manage-records
Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.
worktable-create-or-manage-interactive-html
Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.
worktable-collaborate-threads
Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.