revid-prompt-to-video
Turn a one-line idea into a full short video — Revid writes the script, picks visuals, and assembles the cut. Use when the user has a topic but no script. 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-prompt-to-video
- metadata
- { "openclaw": { "requires": { "config": [ "REVID_API_KEY" ] } } }
- description
- Turn a one-line idea into a full short video — Revid writes the script, picks visuals, and assembles the cut. Use when the user has a topic but no script. Calls the Revid MCP server (render_video → get_project_status).
02 资源文件 2
- 参考文档examples/honey-prompt.json877 B
- 脚本examples/run.sh814 B
03 SKILL.md 正文
Idea prompt → video
The lowest-input skill. The user types one line ("Why honey never spoils") and Revid handles everything: script, visuals, voice, music, cuts.
Calls the Revid MCP server (
https://www.revid.ai/api/mcp). Install once — seerevid-api-foundations.
When to use this skill
- Source is a topic, question, or one-line concept — no script.
- The user is OK letting the AI choose the angle and structure.
- For a known script, use
revid-script-to-video. - For an idea + brand voice, use
revid-product-description-to-ad.
Inputs
| Field | Required | Notes |
|---|---|---|
prompt |
yes | The idea (one or two sentences) |
stylePrompt |
no | Optional tone notes (angle, opener, CTA) |
durationSeconds |
no | Default 35 (s) |
aspectRatio |
no | Default 9:16 |
Step-by-step
- Validate
promptis non-empty. - Call MCP tool
render_videowith the payload below — it returnsdata.pid. - Poll MCP tool
get_project_statuswith thatpidevery 5–8 s untildata.status === "ready"(then readdata.videoUrl). - (Optional) Call
export_videowith{ pid, fileName }if you need a freshly named mp4 export.
render_video arguments
{
"workflow": "prompt-to-video",
"source": {
"prompt": "{ONE_LINE_IDEA}",
"stylePrompt": "{OPTIONAL_TONE_NOTES}",
"durationSeconds": 35
},
"aspectRatio": "9:16",
"voice": { "enabled": true, "stability": 0.6, "speed": 1.0, "language": "en-US" },
"captions": { "enabled": true, "position": "middle", "autoCrop": true },
"music": { "enabled": true, "syncWith": "beats" },
"media": {
"type": "stock-video",
"density": "medium",
"animation": "soft",
"quality": "pro",
"videoModel": "pro",
"imageModel": "good"
},
"options": {
"promptTargetDuration": 35,
"summarizationPreference": "summarizeIfLong",
"soundEffects": true,
"hasToGenerateCover": true
},
"render": { "resolution": "1080p", "frameRate": 30 }
}
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/honey-prompt.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 |
|---|---|
| Script angle is generic ("Did you know…") | Add source.stylePrompt with a specific angle: "Open with a contrarian claim. End with a question that invites comments." |
| Off-niche visuals | Mention concrete subjects in the prompt: "Why honey never spoils — show beehives, ancient Egyptian jars, microscope close-ups of crystallized honey." |
| Too long / too short | Set source.durationSeconds AND options.promptTargetDuration together (some legacy paths only read one). |
ok: false, error: "insufficient_credits" |
Drop media.quality to "standard" or render.resolution to "720p", or call buy_credit_pack. |
See also
revid-api-foundations— auth, MCP install, response envelope.revid-script-to-videowhen you have the words.revid-product-description-to-adfor ads.
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.