agentleFS
yyert123yyert123/miragea-skills/audiogram-clips/SKILL.md

audiogram-clips

Skill0 starsChanged 2 days agoMITView on GitHub

Turn any audio clip (podcast moment, voice note, AI voiceover) into a captioned waveform video for TikTok, YouTube Shorts, Reels, LinkedIn and X. Auto captions from Miragea speech recognition, animated waveform, optional cover art and title, 9:16 / 1:1 / 4:5 / 16:9. Use when the user asks for an audiogram, podcast clip video, podcast to video, video podcast shorts, waveform video, or "make my audio postable". Stdlib Python + ffmpeg.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check MIRAGEA_API_KEY is set (never print it).

    line 17
  2. Very specific:

    Look at a frame (ffmpeg -ss 5 -i out.mp4 -frames:v 1 f.png) before delivering.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Audiogram clips (podcast to video)

Audio-only posts get scrolled past; a moving waveform with burned-in captions gets watched on mute. One command turns a clip into a ready-to-post MP4.

Steps

  1. Check MIRAGEA_API_KEY is set (never print it). Get a free key at https://miragea.ai.
  2. Pick the moment: ask for start/duration (5-90 s works best, hard max 180 s).
  3. Preview the plan for free: python scripts/audiogram.py ep12.mp3 --start 62 --duration 40 --dry-run
  4. Render: python scripts/audiogram.py ep12.mp3 --start 62 --duration 40 --title "Why hooks win" --cover art.jpg --format 9:16 -o ep12-clip.mp4
  5. Look at a frame (ffmpeg -ss 5 -i out.mp4 -frames:v 1 f.png) before delivering. Offer --format 1:1 for LinkedIn/X and --theme light.

Voiceover for the clip? Generate it in the user's cloned voice with the shorts-voiceover or hook-variants skills first, then feed the WAV here.

Why not other tools

Web audiogram makersaudiogram-clips
Price / watermarkPaid tiers, watermark on freeFree, MIT, no watermark
CaptionsManual or extra stepAuto, word-timed via Miragea ASR
PrivacyUpload full episodeOnly the cut mono clip is sent
Agent-readyNoYes, dry-run + one command

FAQ

  • Which formats? 9:16, 1:1, 4:5, 16:9.
  • Offline? --no-captions needs no API.
  • Credits: idea from the audiogram tools (wavve, Headliner, audiogram by NPR, MIT); code is an original rewrite.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.