What does video-speech do?
video-speech is a Codex Skill for extracting spoken commentary from Douyin, Bilibili, and Xiaohongshu videos, and outputting cleaned-up Markdown text.
video-speech is a Codex Skill for extracting spoken commentary from Douyin, Bilibili, and Xiaohongshu videos, and outputting cleaned-up Markdown text.
video-speech is a Codex Skill designed for AI agents to extract and clean up spoken commentary (voiceover) from short-video platforms such as Douyin (TikTok China), Bilibili, and Xiaohongshu (Little Red Book). It is especially useful for developers and content creators who need to retrieve, summarize, or re-purpose video transcripts quickly. The skill runs within Codex agents, processing video content and returning well-formatted Markdown with speech-to-text results that are automatically cleaned of filler words, repetitions, and disfluencies. By integrating with video download and transcription tools, it provides a streamlined pipeline from video URL to polished text, making it a powerful tool for AI-assisted content analysis, data extraction, and workflow automation on these popular Chinese social media platforms.
npx skills add yoYoimiya/video-speechvideo-speech is a Codex Skill for extracting spoken commentary from Douyin, Bilibili, and Xiaohongshu videos, and outputting cleaned-up Markdown text.
Extract frames or short clips from videos using ffmpeg.
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
Obra superpowers agent skills.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...
End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.