Arti Miller
@viralex.aii • 7,858 subscribers
Videos
![AI video editor in Claude Code: 3 prompts, from an empty folder to a finished reel. SETUP (once) 1. Get the Claude app (claude.ai/download) and open the Code tab, not the browser. 2. Make a folder "AI Editor" with 3 folders inside: raw, references, done. 3. New chat in Code → Local → Select folder → AI Editor. Needs a paid Claude plan. PROMPT 1: TOOLS You're my video editor. We work in this folder: raw, references, done. Install and verify 5 tools: FFmpeg with libass (on Mac: ffmpeg-full, full path), faster-whisper for word-level subtitles, yt-dlp for references, Remotion, HyperFrames (npm package hyperframes). Check what's installed first. Official installs only (Homebrew, winget, npm/pip), Node.js 22+. Python packages go in a .venv here, Python 3.14 or older: pip install faster-whisper "av<19". Test each for real: burn a subtitle into a test clip, transcribe 5 seconds of audio. Show a table: tool, version, works or not. PROMPT 2: YOUR TASTE Here are reels whose editing I like: [link 1] [link 2] [link 3]. My format: [talking to camera / voiceover]. Download them with yt-dlp into references (for study only). Study each one frame by frame and by ear: pacing, shot length, pause cuts, subtitles, colors, graphics, transitions, music, the first 3 seconds. Take inspiration, but don't copy: no shots, text, logos or brand elements. Write my own style to style.md with exact values. Show it and ask what to change. PROMPT 3: EDIT My new recording is in raw. Edit it using style.md: 1. Transcribe with Whisper, word timestamps. Ask me about doubtful words before burning subtitles. 2. Cut pauses, slips and bad takes, keep the last good take. Check cut points by audio level. Keep pauses that serve the meaning, breaths and word endings. Don't speed up my voice. 3. Word-by-word subtitles in my style. 4. If references/music.mp3 exists, put it quietly under the voice. 5. Graphics only where they help. 6. Export 1080×1920 to done as draft-v1.mp4 plus edit-notes.md. Check the file yourself, then show me. I'll give edits in plain words; save each as draft-v2, draft-v3. No code words. Follow for my own editing style, coming next.](https://ttanon.com/i/c/7703911645583592736-720.webp)
AI video editor in Claude Code: 3 prompts, from an empty folder to a finished reel. SETUP (once) 1. Get the Claude app (claude.ai/download) and open the Code tab, not the browser. 2. Make a folder "AI Editor" with 3 folders inside: raw, references, done. 3. New chat in Code → Local → Select folder → AI Editor. Needs a paid Claude plan. PROMPT 1: TOOLS You're my video editor. We work in this folder: raw, references, done. Install and verify 5 tools: FFmpeg with libass (on Mac: ffmpeg-full, full path), faster-whisper for word-level subtitles, yt-dlp for references, Remotion, HyperFrames (npm package hyperframes). Check what's installed first. Official installs only (Homebrew, winget, npm/pip), Node.js 22+. Python packages go in a .venv here, Python 3.14 or older: pip install faster-whisper "av<19". Test each for real: burn a subtitle into a test clip, transcribe 5 seconds of audio. Show a table: tool, version, works or not. PROMPT 2: YOUR TASTE Here are reels whose editing I like: [link 1] [link 2] [link 3]. My format: [talking to camera / voiceover]. Download them with yt-dlp into references (for study only). Study each one frame by frame and by ear: pacing, shot length, pause cuts, subtitles, colors, graphics, transitions, music, the first 3 seconds. Take inspiration, but don't copy: no shots, text, logos or brand elements. Write my own style to style.md with exact values. Show it and ask what to change. PROMPT 3: EDIT My new recording is in raw. Edit it using style.md: 1. Transcribe with Whisper, word timestamps. Ask me about doubtful words before burning subtitles. 2. Cut pauses, slips and bad takes, keep the last good take. Check cut points by audio level. Keep pauses that serve the meaning, breaths and word endings. Don't speed up my voice. 3. Word-by-word subtitles in my style. 4. If references/music.mp3 exists, put it quietly under the voice. 5. Graphics only where they help. 6. Export 1080×1920 to done as draft-v1.mp4 plus edit-notes.md. Check the file yourself, then show me. I'll give edits in plain words; save each as draft-v2, draft-v3. No code words. Follow for my own editing style, coming next.
Arti Miller723,800 次观看 • 8 天前
OpenJarvis - a free, open source personal AI assistant you run on your own computer. Made by Stanford researchers (Hazy Research + Scaling Intelligence Lab), not me. #openjarvis #claudecode #aiagents #opensource #ai Repo: github.com/open-jarvis/OpenJarvis Install, Mac / Linux - paste the repo link into Claude Code and say "install this for me", or run it yourself: curl -fsSL open-jarvis.github.io/OpenJarvis/install.sh | bash (add the https prefix to the address) Windows: the install.ps1 command from the README, or the desktop app from Releases. Morning briefing in 3 commands: jarvis init --preset morning-digest-mac --force (or -linux / -minimal) jarvis connect gdrive (one Google sign-in covers Gmail, Calendar, Tasks) jarvis digest --fresh (or just say "good morning" in the chat) If jarvis isn't found, put uv run in front of it. Heads up: - The spoken briefing uses a Cartesia or OpenAI API key (paid). Free: jarvis digest --text-only to read it (a local open source Kokoro voice is also in the code). - Gmail needs your own Google OAuth client (client_id:client_secret), the docs walk you through it. - Models run locally through Ollama, so your computer has to handle a local model. Cloud models are optional. - The installer asks about anonymous analytics - answer N if you don't want it. - The 40 emails in the video are an example, not a test result. No code words - everything's right here. Follow arti.miller - next I'll play you the first real briefing my Jarvis gives me.
Arti Miller30,300 次观看 • 2 天前
没有更多内容可加载