Skip to content

Diogenesoftoronto/keating / video/keating-surface-tour/.agents/skills/media-use

media-use

Flagged

Agent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + ledger record (one verb, `resolve`); generate via TTS / music / image models when the catalog misses; produce voiceover, transcription, captions, and background removal through one shared audio engine; operate on media (cut / reframe / transform); and reuse assets across projects. Also use for vague feedback that real footage looks dark, flat, boring, should feel retro/camcorder/print/ASCII, needs privacy, or needs a media reveal.

FileKindSize
.gitignoreother17 B
SKILL.mdskill md7.8 KB
audio/assets/sfx/CREDITS.mdmarkdown1.2 KB
audio/assets/sfx/chime.mp3binary26.7 KB
audio/assets/sfx/click-soft.mp3binary11.4 KB
audio/assets/sfx/click.mp3binary11.4 KB
audio/assets/sfx/error.mp3binary50.6 KB
audio/assets/sfx/glitch-1.mp3binary82.4 KB
audio/assets/sfx/glitch-2.mp3binary109.5 KB
audio/assets/sfx/glitch-3.mp3binary96.8 KB
audio/assets/sfx/impact-bass-1.mp3binary66.1 KB
audio/assets/sfx/impact-bass-2.mp3binary81.0 KB
audio/assets/sfx/key-press.mp3binary3.8 KB
audio/assets/sfx/manifest.jsonconfig3.6 KB
audio/assets/sfx/notification.mp3binary76.7 KB
audio/assets/sfx/ping.mp3binary25.8 KB
audio/assets/sfx/pop.mp3binary22.5 KB
audio/assets/sfx/riser.mp3binary313.5 KB
audio/assets/sfx/sparkle.mp3binary56.3 KB
audio/assets/sfx/typing.mp3binary26.2 KB
audio/assets/sfx/whoosh-cinematic.mp3binary173.3 KB
audio/assets/sfx/whoosh-short.mp3binary18.0 KB
audio/assets/sfx/whoosh.mp3binary18.0 KB
audio/references/bgm.mdmarkdown7.8 KB
audio/references/captions/authoring.mdmarkdown8.8 KB
audio/references/captions/motion.mdmarkdown5.5 KB
audio/references/captions/transcript-handling.mdmarkdown5.3 KB
audio/references/remove-background.mdmarkdown8.3 KB
audio/references/requirements.mdmarkdown4.2 KB
audio/references/sfx.mdmarkdown3.4 KB
audio/references/transcribe.mdmarkdown2.7 KB
audio/references/tts-to-captions.mdmarkdown1.2 KB
audio/references/tts.mdmarkdown8.6 KB
audio/scripts/audio.mjsscript12.5 KB
audio/scripts/audio.test.mjsscript1.9 KB
audio/scripts/heygen-tts.mjsexecutablescript4.2 KB
audio/scripts/lib/bgm.mjsscript11.3 KB
audio/scripts/lib/bgm.test.mjsscript1.2 KB
audio/scripts/lib/concurrency.mjsscript527 B
audio/scripts/lib/concurrency.test.mjsscript1.6 KB
audio/scripts/lib/heygen.mjsscript6.9 KB
audio/scripts/lib/heygen.test.mjsscript3.5 KB
audio/scripts/lib/python.mjsscript2.5 KB
audio/scripts/lib/python.test.mjsscript2.6 KB
audio/scripts/lib/sfx.mjsscript5.3 KB
audio/scripts/lib/sfx.test.mjsscript2.8 KB
audio/scripts/lib/tts.mjsscript16.1 KB
audio/scripts/lib/tts.spawn.test.mjsscript5.1 KB
audio/scripts/lib/tts.test.mjsscript6.0 KB
audio/scripts/lyria-recipe.pyscript4.4 KB
audio/scripts/wait-bgm.mjsscript5.4 KB
luts/README.mdmarkdown1.1 KB
luts/index.jsonconfig2.0 KB
references/audio.mdmarkdown1.7 KB
references/grading.mdmarkdown6.6 KB
references/media-treatment-recipes.mdmarkdown35.0 KB
references/media-treatments.mdmarkdown13.6 KB
references/memory.mdmarkdown3.3 KB
references/meta.mdmarkdown6.6 KB
references/operations.mdmarkdown14.1 KB
references/resolve.mdmarkdown8.8 KB
references/setup-providers.mdmarkdown7.1 KB
references/telemetry-dashboard.mdmarkdown4.1 KB
scripts/audio-duck.mjsscript3.9 KB
scripts/dither.mjsscript9.7 KB
scripts/dither.test.mjsscript4.6 KB
scripts/eval.mjsscript14.5 KB
scripts/lib/adopt.mjsscript4.3 KB
scripts/lib/adopt.test.mjsscript2.7 KB
scripts/lib/bgm-provider.mjsscript650 B
scripts/lib/brand-provider.mjsscript1.6 KB
scripts/lib/bundled-sfx-provider.mjsscript3.5 KB
scripts/lib/bundled-sfx-provider.test.mjsscript3.1 KB
scripts/lib/cache.mjsscript4.8 KB
scripts/lib/candidates.mjsscript4.0 KB
scripts/lib/candidates.test.mjsscript5.9 KB
scripts/lib/codex-provider.mjsscript6.5 KB
scripts/lib/codex-provider.test.mjsscript1.3 KB
scripts/lib/coverage.test.mjsscript5.6 KB
scripts/lib/cube-build.mjsscript5.7 KB
scripts/lib/cube-build.test.mjsscript2.7 KB
scripts/lib/cube-validate.mjsscript5.9 KB
scripts/lib/cube-validate.test.mjsscript3.2 KB
scripts/lib/cutlist.mjsscript6.0 KB
scripts/lib/cutlist.test.mjsscript4.0 KB
scripts/lib/duck.mjsscript3.0 KB
scripts/lib/duck.test.mjsscript3.4 KB
scripts/lib/error-diffusion.mjsscript6.5 KB
scripts/lib/error-diffusion.test.mjsscript3.4 KB
scripts/lib/freeze.mjsscript3.0 KB
scripts/lib/freeze.test.mjsscript1.9 KB
scripts/lib/grade-analyzer.mjsscript8.6 KB
scripts/lib/grade-analyzer.test.mjsscript7.7 KB
scripts/lib/heygen-cli.mjsscript7.3 KB
scripts/lib/heygen-cli.test.mjsscript10.0 KB
scripts/lib/heygen-search.mjsscript1.8 KB
scripts/lib/heygen-search.test.mjsscript1.8 KB
scripts/lib/heygen-video-provider.mjsscript3.6 KB
scripts/lib/heygen-video-provider.test.mjsscript12.0 KB
scripts/lib/image-provider.mjsscript1.4 KB
scripts/lib/index-gen.mjsscript1.9 KB
scripts/lib/local-models.mjsscript13.3 KB
scripts/lib/local-models.test.mjsscript5.6 KB
scripts/lib/local-run.mjsscript2.2 KB
scripts/lib/local-run.test.mjsscript1.7 KB
scripts/lib/logo-provider.mjsscript7.0 KB
scripts/lib/logo-provider.test.mjsscript5.7 KB
scripts/lib/ltx-video-provider.mjsscript1.9 KB
scripts/lib/ltx-video-provider.test.mjsscript3.8 KB
scripts/lib/lut-preset-provider.mjsscript8.5 KB
scripts/lib/lut-preset-provider.test.mjsscript6.3 KB
scripts/lib/manifest.mjsscript7.0 KB
scripts/lib/manifest.test.mjsscript11.6 KB
scripts/lib/match.mjsscript1.4 KB
scripts/lib/mflux-provider.mjsscript3.2 KB
scripts/lib/misses.mjsscript1.2 KB
scripts/lib/misses.test.mjsscript2.5 KB
scripts/lib/npx-sync.mjsscript1.3 KB
scripts/lib/npx-sync.test.mjsscript2.0 KB
scripts/lib/parakeet-words.mjsscript1.1 KB
scripts/lib/parakeet-words.test.mjsscript1.4 KB
scripts/lib/prefs-store.mjsscript6.4 KB
scripts/lib/prefs-store.test.mjsscript7.2 KB
scripts/lib/probe.mjsscript1.3 KB
scripts/lib/probe.test.mjsscript1.6 KB
scripts/lib/providers.mjsscript327 B
scripts/lib/recipe-store.mjsscript12.7 KB
scripts/lib/recipe-store.test.mjsscript12.5 KB
scripts/lib/registry.mjsscript9.5 KB
scripts/lib/registry.test.mjsscript9.6 KB
scripts/lib/search.mjsscript906 B
scripts/lib/search.test.mjsscript1.2 KB
scripts/lib/sfx-provider.mjsscript700 B
scripts/lib/specs.mjsscript3.2 KB
scripts/lib/specs.test.mjsscript2.7 KB
scripts/lib/stats.mjsscript3.7 KB
scripts/lib/stats.test.mjsscript5.4 KB
scripts/lib/telemetry.mjsscript8.3 KB
scripts/lib/telemetry.test.mjsscript13.1 KB
scripts/lib/tts-local-provider.mjsscript3.7 KB
scripts/lib/tts-local-provider.test.mjsscript2.6 KB
scripts/lib/usage.mjsscript1.8 KB
scripts/lib/usage.test.mjsscript1.7 KB
scripts/lib/voice-provider.mjsscript1.7 KB
scripts/lib/voice-provider.test.mjsscript1.9 KB
scripts/lib/words.mjsscript764 B
scripts/prefs.mjsscript2.4 KB
scripts/recipe.mjsscript4.0 KB
scripts/resolve.mjsscript43.2 KB
scripts/resolve.test.mjsscript35.8 KB
scripts/transcribe.mjsscript6.5 KB
scripts/transcript-cut.mjsscript7.1 KB

audio/references/bgm.md

View on GitHub
# Background music (BGM)

One music bed per composition, produced by the shared audio engine (`scripts/audio.mjs` → `scripts/lib/bgm.mjs`). Two routes, chosen by the engine's one switch — whether a HeyGen credential is present:

- **HeyGen retrieval — the default when credentialed.** Search HeyGen's music catalog by mood, download the top track. No generation; same `~/.heygen` / `$HEYGEN_API_KEY` credential as TTS.
- **Local generation (Lyria → MusicGen) — the fallback when there is no credential** (or when asked for explicitly). Generate a WAV from a mood prompt. There is **no `npx hyperframes bgm` command**; the engine spawns `scripts/lyria-recipe.py` or an inline MusicGen script directly.

> **Run the Preflight first — no credential is not a green light to silently generate locally.** Before generating, complete the sign-in **Preflight** (see `../SKILL.md` → Preflight): run `npx hyperframes auth status`, recommend signing in, and **STOP for the user's choice** (sign in for HeyGen's music library, or continue offline with local generation). This applies to a one-off "generate a BGM" request just as much as inside a full workflow.

## Driving it from the request

`audio_request.json` → `bgm: { mode?, query?, prompt? }`:

- **`mode`** — `retrieve | generate | none`. Omit for **auto** (retrieve when credentialed, else generate). An **explicit** `retrieve` is strict: no credential ⇒ skip, never a detached generate (so a caller with no `wait-bgm` step, e.g. product-launch, can't get a pending job it won't await).
- **`query`** — the mood, used for retrieval and as a fallback prompt seed (e.g. a storyboard's `music:` field, falling back to `message` → `arc` → `"calm cinematic underscore"`).
- **`prompt`** — an explicit full prompt for generation; omit and the engine infers one (see Mood inference). Optional `blob` / `archetype` / `arc` feed that inference.

## HeyGen retrieval (default)

`searchSounds(query, "music", { limit: 5 })` → `GET /audio/sounds?query=<mood>&type=music&limit=5`. Take the top result (ranked by `score`), download its presigned `audio_url` → `assets/bgm/track.mp3`. Synchronous. No match → skip (BGM is optional; never fail the render over it). Cue written to `audio_meta.json`:

```jsonc
{
  "path": "assets/bgm/track.mp3",
  "volume": 0.12,
  "mode": "retrieve",
  "query": "calm cinematic underscore",
  "duration_s": 42.0,
}
```

`volume` comes from the engine's `bgmDefaultVolume()`: `BGM_BED_VOLUME` (currently `0.12` ≈ -18 dB — a bed under the voice) under narration, `BGM_SILENT_VOLUME` (currently `0.9`) for a silent film (no voice). Tune those constants in `scripts/lib/bgm.mjs`, not call sites. An explicit `volume` in `audio_meta.json` always overrides this default. `bgm_pending` is `false` — the file is on disk when the engine returns.

For short launch videos, do not assume the beginning of the retrieved file is the best edit point. Check the opening against later five-second sections. If the track starts with a quiet build but a later section has a stronger, clean musical entrance, trim from that section and apply a short fade-in and longer fade-out. Repeat this check whenever the composition duration changes; the final music file must cover the full cut without a silent tail.

## Local generation (fallback) — Lyria → MusicGen

Spawned **detached** so voice work isn't blocked; `audio_meta.bgm_pending: true` and `bgm_pid` / `bgm_log` are set until it finishes. **Run `scripts/wait-bgm.mjs` before assembling** — it polls the output file / process / log, detects crashes, and writes `bgm_status.json` (`status: ready | failed | timeout | disabled`). A failed/absent track is simply omitted; it never blocks voice/SFX.

| Order | Provider                             | Env / deps                                                                            | Speed                                   | Quality                     |
| ----- | ------------------------------------ | ------------------------------------------------------------------------------------- | --------------------------------------- | --------------------------- |
| 1     | Google Lyria RealTime                | `$GEMINI_API_KEY` or `$GOOGLE_API_KEY` + `google-genai` (auto-installed on demand)    | Real-time stream (≈ requested duration) | Production-grade            |
| 2     | MusicGen (`facebook/musicgen-small`) | Python `transformers + torch + soundfile + numpy` (~300 MB first run; auto-installed) | Slow on CPU; fast on Apple MPS / CUDA   | Decent; prompt-only control |

Output → `assets/bgm/track.wav`, target = total voice duration. MusicGen generates **one** seed clip (≤28–30s, under the decoder's positional limit) then crossfade-loops it up to the target (or trims down if shorter), avoiding per-segment seams. Backend selection is by what can actually **run**: Lyria only when `import google.genai` succeeds, else MusicGen; if neither can be made to run, BGM is skipped (voice + SFX still render).

## Mood inference (the generate prompt)

`inferBgmPrompt()` in `scripts/lib/bgm.mjs`: an explicit `prompt` wins; otherwise industry-keyword **base** → narrative-**archetype** shape → emotional-**arc** tiebreaker.

| Match in `blob` / `query`                              | Base prompt                                                                 | BPM |
| ------------------------------------------------------ | --------------------------------------------------------------------------- | --- |
| `crypto / nft / web3 / defi / token / blockchain`      | atmospheric electronic, deep bass, futuristic synths, restrained percussion | 100 |
| `finance / fintech / bank / payment / invest / wealth` | calm cinematic, soft strings, subtle piano, restrained percussion           | 92  |
| `creative / agency / design / studio / art / brand`    | playful electronic, warm pads, light percussion                             | 115 |
| _(default: SaaS / tech / platform)_                    | uplifting corporate tech, bright modern piano with synth pads               | 108 |

Archetype then reshapes the arc — PAS → "MINOR to MAJOR" build; BAB / future-pacing → aspirational rising; feature-cascade → +10 BPM driving; demo-loop → −8 BPM minimal. The emotional arc breaks remaining ties (tension→relief, excitement, trust/reassurance).

## Lyria knobs (direct recipe use)

The engine bakes BPM / scale into the **prompt text** (via the inference above) and passes only `--output` / `--duration` / `--prompt` to the recipe. If you invoke `scripts/lyria-recipe.py` directly you can also set: `--bpm` (90–110 calm, 110–130 energetic), `--brightness` (0–1, ≥0.7 promotional), `--density` (0–1, higher = fuller), `--scale` (`MAJOR` / `MINOR` / `PENTATONIC` / …), `--negative-prompt` (styles to exclude). MusicGen ignores all of these — put the mood in the prompt.

## Failure modes

| Failure                                       | Behavior                                                                                 |
| --------------------------------------------- | ---------------------------------------------------------------------------------------- |
| No music match (retrieve)                     | `bgm: null`, anomaly logged. Render proceeds without BGM.                                |
| Explicit `retrieve`, no credential            | Skipped (no silent generate fallback). Use `mode: generate` or omit `mode` for auto.     |
| Neither Lyria nor MusicGen can run (generate) | `bgm` disabled with a `pip install …` hint. Voice + SFX still render.                    |
| Generate still rendering at assemble time     | `bgm_pending: true`; `wait-bgm.mjs` waits/checks and writes `bgm_status.json` first.     |
| Generate crashed                              | `wait-bgm.mjs` → `bgm_status.json { status: "failed" }`; the `<audio>` track is omitted. |

BGM failure never blocks a render.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall