revid-script-to-video
Turn an already-written script into a video with voiceover, auto-cut stock visuals, and captions. Use when the user has the words and wants Revid to handle production. 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-to-video
- metadata
- { "openclaw": { "requires": { "config": [ "REVID_API_KEY" ] } } }
- description
- Turn an already-written script into a video with voiceover, auto-cut stock visuals, and captions. Use when the user has the words and wants Revid to handle production. Calls the Revid MCP server (render_video → get_project_status).
02 资源文件 2
- 参考文档examples/honey-script.json1.1 KB
- 脚本examples/run.sh965 B
03 SKILL.md 正文
Script → video
Calls the Revid MCP server (
https://www.revid.ai/api/mcp). Install once — seerevid-api-foundations.
The script-to-video workflow is the lowest-friction path: you bring the words, Revid brings the visuals + voice + captions + edit.
When to use this skill
- The user pastes a finished script (or generates one in-conversation).
- They want full creative control over the words.
- They are happy with stock visuals (otherwise see
revid-script-with-custom-media). - For an idea-to-video flow, use
revid-prompt-to-video.
Inputs
| Field | Required | Notes |
|---|---|---|
text |
yes | The script. Use line breaks for scene boundaries. |
aspectRatio |
no | Default 9:16 |
voiceId |
no | Pick to match the script tone |
targetDuration |
no | Auto-derived from script length if omitted |
Step-by-step
- Validate
textis non-trivial (>30 words) and within practical limits (~1500 words for a 5-min video). - Call MCP tool
render_videowith the payload below — returnsdata.pid. - Then poll MCP tool
get_project_statuswith thatpidevery 5–8 s untildata.status === "ready"(readdata.videoUrl). 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, "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": {
"summarizationPreference": "no-summarization",
"soundEffects": true,
"hasToGenerateCover": true
},
"render": { "resolution": "1080p", "frameRate": 30 }
}
summarizationPreference: "no-summarization" — the user wrote the script for a
reason. Don't paraphrase it.
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-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.
Failure modes
| Symptom | Fix |
|---|---|
| Script too long → exceeds context | Either split into multiple render_video calls (one per chapter) or set summarizationPreference: "summarize". |
| Voice mispronounces brand names | Inline phonetic spelling in the script ("Revid (rev-id)"). |
| Visuals don't match niche topic | Pre-author a few key shots and switch to revid-script-with-custom-media. |
| Music drowns the voice | Lower music duck — currently no direct knob; switch music.enabled: false and add ambient sound effects via options.soundEffects: true. |
ok: false, error: "insufficient_credits" |
Drop media.quality to "standard" or render.resolution to "720p", or call buy_credit_pack. |
See also
revid-script-with-custom-mediafor full visual control.revid-prompt-to-videowhen you want Revid to write the script too.revid-tweet-to-talking-headfor short scripts with an avatar.
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.