video-transcript-workflow视频/音频转录 → 优化润色 → 多平台发布稿。使用 faster-whisper 转录音视频,自动修正错误、提取金句、生成知乎/微信/小红书等多平台文章。Use when user wants to transcribe video/audio, convert speech to text, or creat...
Install via ClawdBot CLI:
clawdbot install artminding/video-transcript-workflowGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://openclaw.aiAudited Apr 22, 2026 · audit v1.0
Generated Oct 26, 2026
A solo creator uploads a long interview or tutorial video and needs a clean transcript plus polished articles for Zhihu, WeChat, and Xiaohongshu without manually rewriting. The skill transcribes with faster-whisper, fixes terminology, extracts golden quotes, and outputs platform-specific drafts. It removes hours of manual editing and republishing work.
L&D teams record internal training sessions or all-hands meetings and need accurate transcripts with terminology corrections and structured summaries. The skill produces time-coded optimized transcripts and polished write-ups while preserving original meaning. This helps build searchable knowledge bases faster.
Podcast producers record episodes and need transcripts, show notes, and social clips. The skill handles transcription, removes filler words, highlights key insights, and generates short-form Xiaohongshu and WeChat posts. It also extracts quotable soundbite text for promotion.
Online course creators record lessons and want supplementary reading materials and marketing content. The skill converts lesson audio/video into optimized transcripts with glossary notes and background knowledge, plus platform posts for audience growth. This lets course teams reuse one lesson across multiple channels.
Consultants and analysts record client workshops or webinars and want to turn spoken insights into authoritative articles. The skill preserves the expert's voice, corrects technical terms, and adapts tone for Zhihu rationality and WeChat storytelling. It converts one recording into a full publishing pipeline.
Offer the workflow as a monthly subscription where users upload files and receive transcripts and multi-platform drafts. Tiered by minutes transcribed per month and number of platform outputs. Targets podcasters, YouTubers, and course creators who publish frequently.
Sell to L&D, marketing, and consulting firms as a team tool with shared workspace, terminology dictionaries, brand style presets, and approval workflows. Includes audit trails and low-confidence correction review queues for compliance. Priced per seat or per transcribed hour.
Operate a managed service or white-label API that delivers finished platform articles for agencies and media companies. Combine automated transcription with human editors reviewing low-confidence corrections and brand voice. Charge per completed article bundle or per project.
💬 Integration Tip
Wire the workflow into existing storage and publishing tools (e.g., cloud drive trigger, CMS/WeChat draft push) and keep a terminology dictionary plus MEMORY.md user-preference profile to improve auto-correction and platform tone over time.
Scored Jun 14, 2026
视频自动剪辑助手。基于 FFmpeg 自动提取精彩片段、生成字幕、裁剪时长、制作短视视频,支持多平台导出。当用户需要:自动剪辑视频、提取关键词片段、生成字幕并烧录、导出短视频、提取视频精华、生成视频摘要时使用此技能。
Perform video editing tasks with ffmpeg, including cutting, merging, converting formats, extracting audio, adding subtitles, resizing, cropping, adjusting sp...
When the user wants to optimize signup, registration, account creation, or trial activation flows. Also use when the user mentions "signup conversions," "reg...
Use when the user has a video + a target-language SRT and wants the video to actually speak that language — generates a time-aligned TTS voice dub. Routes by...
Extract frames or short clips from videos using ffmpeg.
本地视频转文字 - 使用 OpenAI Whisper 进行语音识别,完全免费、离线运行、保护隐私