Communitygithub.com

review-ugc-render

UGC视频渲染的强制性发布前审核关卡:使用Whisper转录最终渲染文件的音频,并与获批的脚本进行单词级对比,阻止存在语音错误的渲染进入发布流程。

review-ugc-render 是什么?

该技能是UGC视频渲染管线的强制性发布前审核关卡,确保生成的音频与用户批准的脚本完全一致。它通过Whisper转录最终渲染文件的音频,并进行单词级差异对比,能够检测出单词误读(如将“human-vetted”读成“human witted”)、遗漏获批短语或整个音频静音等缺陷。该技能是内容鹅审核引擎中“review-transcript-integrity”轴的部署化、门控版本,支持多种转录后端,并生成详细的JSON诊断报告。它必须作为每个remix-ugc和create-ugc视频制作流程的一部分,在最终渲染之后、set_final_render之前运行,只有退出码为0时才允许发布。

兼容平台~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/gooseworks-ai/goose-skills/tree/HEAD/skills/ads/packs/ugc-video-formats/review-ugc-render

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

review-ugc-render 是做什么的?

每个UGC视频制作流程在发布前必须通过的QC审核关卡。这不是肉眼观察的/watch——而是一个确定性的转录vs脚本差异检查,一旦发现缺陷即非零退出,使流程能够硬阻止set_final_render。

为什么存在这个技能

Seedance是原生生成音频的。它有时会将单词读错——获批的台词human-vetted被读成human witted;已知的同类型问题包括:Hume→Hune,Alitu→al-too。缺陷存在于渲染的音频中,因此肉眼观察/watch(“对话与脚本匹配”)会遗漏问题,而下游的字幕处理会将错误单词原封不动地嵌入视频。之前没有任何机制将实际说出的音频与用户批准的脚本进行对比。

这个审核关卡正是以确定性的方式完成这一对比,并在发现不匹配时拒绝发布。

何时运行

  • 必须在每个remix-ugc-*-from-sample和create-ugc-*-video-from-refs制作流程的QC阶段中运行,即在主渲染存在之后、set_final_render之前。
  • 在每次修复/重新渲染后重新运行,直到通过(PASS)为止。

约定

在渲染之前,将批准的台词原文(逐字说出的话语,不含语气备注)保存到working/approved-script.txt。然后在渲染后运行:

python3 <pack>/review-ugc-render/scripts/review_render.py \
  --video working/final.mp4 \
  --script-file working/approved-script.txt \
  --json working/review-verdict.json
  • 退出码 0 → 通过 — 继续发布(set_final_render)。
  • 退出码 2 → 失败 — 不要发布。阅读报告,修复,重新运行。
  • 退出码 3 → 错误 — 检查无法运行(见下文);修复环境,不要盲目发布。

转录后端(优先级顺序):OPENAI_API_KEY(遵循OPENAI_BASE_URL,因此当设置时它会通过gooseworks Whisper代理路由)→ 本地whisper CLI。环境中必须存在ffmpeg。

失败(FAIL)的含义及如何修复

报告行根本原因修复方法
[high] said [witted] where script has [vetted]Seedance在生成的音频中读错了单词重新生成一个新的种子。 如果是品牌/自创词汇,在SPOKEN LINE中用音标拼写出来(例如Ali-too,永远不要使用(发音 …)这样的括号——Seedance会把括号内容读出来)。参见create-video-seedance-2-fal失败模式。
[medium] dropped [...] / 相似度低Seedance漏掉了批准的短语重新生成;如果只是尾部单词遗漏,可能可以通过精准的stitch_replacement.py窗口修复来恢复。
⚠ audio is effectively silent错误的渲染/音频轨道在后期处理中丢失重新渲染/重新检查混流;永远不要发布静默的片段。
ERROR: no transcription backend没有设置OPENAI_API_KEY,也没有本地whisper设置密钥(代理OPENAI_BASE_URL)或安装whisper,然后重新运行。

--expect-music仅为参考(如果缺少背景音乐则发出警告);它本身不会导致审核关卡失败。

输入

  • --video PATH(必需)——已渲染的主mp4文件。
  • --script-file PATH 或 --script "text"——已批准的对话脚本。两者都省略仅用于真正没有脚本的片段(此时跳过一致性检查,审核关卡仅作为参考)。
  • --min-ratio FLOAT(默认0.90)——通过检查所需的转录与脚本的token相似度。
  • --json PATH——将机器判定结果写入文件,供应用的审核面板使用。

测试

python3 tests/test_review_render.py    # 纯判定逻辑;不涉及音频/网络

涵盖经典的vetted→witted误读、品牌名称误读、尾部遗漏、无害填充词,以及无脚本的参考路径。

与内容鹅审核引擎的关系

这是更完整的coworkers/video/molecules/review/review-loop(18维度评分体系)中已发布、单文件、门控形式的切片。在这里,我们强制执行在发布时能够捕捉音频与脚本缺陷的那一个维度(review-transcript-integrity / brand_text_accuracy)。更深层次的多维度审核保留在内容鹅实验室中。

Individual skills in this repo

This repo contains 10 individual skills — each has its own dedicated page.

gooseworks-ai/goose-skills

Burned-in captions for a finished vertical video, three kinds. transcribe.py gets word timings from the video's own audio through the GooseWorks proxy (fal Whisper, bills the Ads agent, cents); captions.py burns one to three words at a time with Pillow + ffmpeg (no libass needed), either pinned to a split-screen seam (plate 25% above / 75% below) or at a fixed height, in a plate, outline or one-word serif style, with an optional red hook card; plates.py burns per-beat caption blocks (black, one union silhouette, placed in the emptiest band) for formats with no voice. The last caption (the CTA) holds to the final frame. Use as the last step of any video ad.

gooseworks-ai/goose-skills

Assemble a cartoon / animated / hand-crafted music-video ad from a config — a sung song carries the whole narrative while N per-bar i2v clips (one recurring animated character, one look pack) are each cut to their BAR window from librosa beat-tracking and hard-concatenated on the bar, VEED-whisper white bold-sans captions in the BOTTOM third (Alignment 2, above the logo bug, no pill) burned from the song's word timings re-spelled against the locked lyrics, a persistent brand logo bug held over the body (suppressed on the end card), and closed on a solid-brand-color PIL end card with the song still playing under it — never AI-rendered text. This is the FREE deterministic assembly stage (cut-to-bar + hard concat + logo bug + captions + end card + song mux); the song, character, keyframes, and clips come from create-music-elevenlabs / create-image-fal / create-video-fal. Use for the cartoon-music-video format.

gooseworks-ai/goose-skills

Assemble a cinematic live-action-style music-video ad from a config — an original sung anthem carries the whole narrative while N 35mm-film-look i2v clips are each cut to their lyric window and hard-concatenated on the beat as a 3-act arc, the anthem muxed at loudnorm I=-14, cinematic lower-third serif captions built from the song's OWN word timings (never Whisper) with the hook line landing on the chorus drop, and closed on a brand end card composited from the real asset — never AI-rendered text. This is the FREE deterministic assembly stage (cut-to-window + hard concat + anthem mux + captions + end card); the anthem, keyframes, and clips come from create-music-elevenlabs / create-image-gpt-image-fal / create-video-fal. Use for the cinematic-music-video format.

gooseworks-ai/goose-skills

Assemble an editorial-motion podcast-clip ad from a config — a real clipped podcast MP3 carries the narrative while N flat limited-palette editorial-illustration keyframes (one look pack) are animated NOT by generative i2v but by DETERMINISTIC ffmpeg ken-burns (zoompan) + hard cuts (no crossfades, which expose geometric drift), each beat snapped to its spoken line, the real audio muxed, Whisper-driven captions burned only mid-sentence, and closed on a PIL brand end card — never AI-rendered text. This is the FREE deterministic assembly stage (ffmpeg ken-burns + hard concat + audio mux + captions + end card); the real audio is clipped from source and the keyframes come from create-image-fal. Use for the editorial-motion-podcast format.

gooseworks-ai/goose-skills

Analyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries through to the landing page headline, body, and CTA. Flags disconnects that kill conversion rates. Works with Google, Meta, and LinkedIn ads.

gooseworks-ai/goose-skills

Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills the Ads agent). The default clip atom for AI-creator UGC ads built on the NB2 + Seedance architecture. Validated on beauty-by-earth/video-01.

gooseworks-ai/goose-skills

Render pixel-accurate Apple Notes (iPhone, light mode) screenshot mockups from a JSON note spec. Outputs HTML + PNG at the iPhone 16/15 Pro native 1180×2556. Supports paragraphs, images, checklists, dividers, autocorrect underline, smart quotes, and an optional iOS keyboard chrome overlay used by the parent video-ad molecule.

gooseworks-ai/goose-skills

Extract competitor and customer intelligence from any company's landing page HTML. Discovers tech stack, analytics tools, ad pixels, customer logos, SEO metadata, CTAs, hidden elements, and more. No API keys required.

gooseworks-ai/goose-skills

Find speakers, hosts, and guest profiles at conferences and events on Luma. Two modes - free direct scrape for hosts, or Apify-powered search for full guest profiles with LinkedIn/Twitter/bio.

gooseworks-ai/goose-skills

Find Twitter/X influencers to promote a product or brand. Use when asked to find influencers, discover Twitter accounts for partnerships, identify creators in a niche, or build an influencer outreach list.

相关技能