LeoHUANG
Agents
Ask Codex what was said at 12:40, and what the slide on screen actually read. Real Video for Codex turns any video into keyframes, a transcript and on-screen text with timecodes, processing on your machine; Codex answers with timestamps. Needs the Codex CLI installed and signed in. Codex sends that text and those frames to OpenAI and uses your ChatGPT quota. Ships with the skill and a doctor self-check. Already own crv Pro? Both arrive free in the next Pro version.
Open-source CLI (MIT, 2k+ GitHub stars, Hacker News front page). Turn any video URL or local file into scene-aware keyframes plus a timestamped, speaker-labeled transcript your LLM can actually read. - Runs 100% on your machine, nothing is uploaded - Works with Claude, ChatGPT, Gemini or local models - URL videos reuse the platform's own captions, Whisper otherwise New in 0.10.5: Apple Silicon GPU transcription, about 6x faster on M-series Macs, same no-fake-captions gate.
Watch the 60s film: https://youtu.be/sw6_8E-57w4 Pro adds to free claude-real-video: - camera & pacing (--motion) - voice emotion (--senses) - speaker labels (--speakers) - synced viewer (--viewer) - AI reports (--ai-report) New in 0.10.5: Apple Silicon GPU transcription. A 21-min talk in about a minute on an M4; music or silence never becomes fake captions. Built on open-source claude-real-video (2k+ GitHub stars, HN front page). Runs on your machine; only --ai-report uses your own API key.