revid-pdf-to-video
Turn a PDF (whitepaper, ebook chapter, slide deck export, research paper) into a short summary video. Use when the source is a PDF URL or a PDF the agent can upload to public storage first. 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-pdf-to-video
- metadata
- { "openclaw": { "requires": { "config": [ "REVID_API_KEY" ] } } }
- description
- Turn a PDF (whitepaper, ebook chapter, slide deck export, research paper) into a short summary video. Use when the source is a PDF URL or a PDF the agent can upload to public storage first. Calls the Revid MCP server (render_video → get_project_status).
02 资源文件 2
- 脚本examples/run.sh789 B
- 参考文档examples/whitepaper.json866 B
03 SKILL.md 正文
PDF → summary video
Calls the Revid MCP server (
https://www.revid.ai/api/mcp). Install once — seerevid-api-foundations.
Take a PDF URL and produce a short summary video. Internally this routes
through article-to-video once the PDF text has been extracted by Revid's
scraper.
When to use this skill
- Source is a public PDF URL (whitepaper, paper, ebook, slide export).
- Goal is a 30–90 s summary, not a full reading.
- For HTML articles use
revid-article-to-short. - For local PDFs the agent must first upload to public storage (S3, Supabase Storage, etc.) so Revid can fetch it.
Inputs
| Field | Required | Notes |
|---|---|---|
url |
yes | Public PDF URL (must be reachable, no auth) |
aspectRatio |
no | Default 9:16 |
targetDuration |
no | Default 60 (s); raise to 90 s for dense papers |
Step-by-step
- Confirm the URL ends in
.pdfor returnsContent-Type: application/pdf. - Set
source.scrapingPromptto bias the summary toward what the user cares about ("Focus on the methodology section", "Focus on the executive summary", "Pull the 3 biggest takeaways"). - Call MCP tool
render_videowith the payload below — 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": "article-to-video",
"source": {
"url": "{PDF_URL}",
"scrapingPrompt": "Extract the executive summary and the 3 biggest takeaways. Skip references and appendices."
},
"aspectRatio": "9:16",
"voice": { "enabled": true, "stability": 0.65, "speed": 0.95, "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",
"imageModel": "good",
"videoModel": "pro"
},
"options": {
"targetDuration": 60,
"summarizationPreference": "summarize",
"soundEffects": true,
"hasToGenerateCover": true,
"coverTextType": "title"
},
"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/whitepaper.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 |
|---|---|
scrape failed |
PDF behind auth or login wall. Re-host the PDF on public storage. |
| Summary skips the section the user cares about | Tighten scrapingPrompt (be specific: section names, page ranges). |
| Visuals are abstract / off-topic | PDFs rarely have crawlable hero images. Pre-render a few key figures as images and pass them in media.provided. |
| Voice rushes through technical terms | Lower voice.speed to 0.9. |
ok: false, error: "insufficient_credits" |
Drop media.quality to "standard" or render.resolution to "720p", or call buy_credit_pack. |
See also
revid-article-to-shortfor HTML.revid-script-with-custom-mediafor full visual control.
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.