media-use
Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 3
- Forks
- 0
01 前言 Front Matter
- name
- media-use
- description
- Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.
02 资源文件 121
- 其他.gitignore17 B
- 资产文件audio/assets/sfx/chime.mp326.7 KB
- 资产文件audio/assets/sfx/click-soft.mp311.4 KB
- 资产文件audio/assets/sfx/click.mp311.4 KB
- 参考文档audio/assets/sfx/CREDITS.md1.2 KB
- 资产文件audio/assets/sfx/error.mp350.6 KB
- 资产文件audio/assets/sfx/glitch-1.mp382.4 KB
- 资产文件audio/assets/sfx/glitch-2.mp3109.5 KB
- 资产文件audio/assets/sfx/glitch-3.mp396.8 KB
- 资产文件audio/assets/sfx/impact-bass-1.mp366.1 KB
- 资产文件audio/assets/sfx/impact-bass-2.mp381.0 KB
- 资产文件audio/assets/sfx/key-press.mp33.8 KB
- 参考文档audio/assets/sfx/manifest.json3.6 KB
- 资产文件audio/assets/sfx/notification.mp376.7 KB
- 资产文件audio/assets/sfx/ping.mp325.8 KB
- 资产文件audio/assets/sfx/pop.mp322.5 KB
- 资产文件audio/assets/sfx/riser.mp3313.5 KB
- 资产文件audio/assets/sfx/sparkle.mp356.3 KB
- 资产文件audio/assets/sfx/typing.mp326.2 KB
- 资产文件audio/assets/sfx/whoosh-cinematic.mp3173.3 KB
- 资产文件audio/assets/sfx/whoosh-short.mp318.0 KB
- 资产文件audio/assets/sfx/whoosh.mp318.0 KB
- 参考文档audio/references/bgm.md7.9 KB
- 参考文档audio/references/captions/authoring.md9.2 KB
- 参考文档audio/references/captions/motion.md5.4 KB
- 参考文档audio/references/captions/transcript-handling.md5.3 KB
- 参考文档audio/references/remove-background.md8.3 KB
- 参考文档audio/references/requirements.md4.4 KB
- 参考文档audio/references/sfx.md4.0 KB
- 参考文档audio/references/transcribe.md2.8 KB
- 参考文档audio/references/tts-to-captions.md1.7 KB
- 参考文档audio/references/tts.md13.7 KB
- 脚本audio/scripts/audio.mjs14.2 KB
- 脚本audio/scripts/audio.test.mjs5.9 KB
- 脚本audio/scripts/carve.mjs23.3 KB
- 脚本audio/scripts/carve.test.mjs11.5 KB
- 脚本audio/scripts/extract-audio-data.py7.0 KB
- 脚本audio/scripts/gemini-pipeline.test.mjs4.8 KB
- 脚本audio/scripts/heygen-tts.mjs4.3 KB
- 脚本audio/scripts/heygen-tts.test.mjs1.4 KB
- 脚本audio/scripts/heygen-voice.mjs3.8 KB
- 脚本audio/scripts/heygen-voice.test.mjs8.3 KB
- 脚本audio/scripts/lib/audio-meta.mjs1.1 KB
- 脚本audio/scripts/lib/audio-meta.test.mjs4.5 KB
- 脚本audio/scripts/lib/bgm-volume.mjs236 B
- 脚本audio/scripts/lib/bgm.mjs11.3 KB
- 脚本audio/scripts/lib/bgm.test.mjs2.6 KB
- 脚本audio/scripts/lib/concurrency.mjs527 B
- 脚本audio/scripts/lib/concurrency.test.mjs1.6 KB
- 脚本audio/scripts/lib/gemini-auth_test.py4.3 KB
- 脚本audio/scripts/lib/gemini-auth.mjs1.6 KB
- 脚本audio/scripts/lib/gemini-auth.py1.9 KB
- 脚本audio/scripts/lib/gemini-auth.test.mjs3.0 KB
- 脚本audio/scripts/lib/gemini-tts.mjs5.0 KB
- 脚本audio/scripts/lib/gemini-tts.test.mjs9.2 KB
- 脚本audio/scripts/lib/heygen.mjs13.0 KB
- 脚本audio/scripts/lib/heygen.test.mjs16.3 KB
- 脚本audio/scripts/lib/main-module.mjs479 B
- 脚本audio/scripts/lib/media-record.mjs4.2 KB
- 脚本audio/scripts/lib/media-record.test.mjs8.3 KB
- 脚本audio/scripts/lib/openverse.mjs4.9 KB
- 脚本audio/scripts/lib/python.mjs4.1 KB
- 脚本audio/scripts/lib/python.test.mjs7.1 KB
- 脚本audio/scripts/lib/recording.mjs2.1 KB
- 脚本audio/scripts/lib/sfx.mjs7.2 KB
- 脚本audio/scripts/lib/sfx.test.mjs11.6 KB
- 脚本audio/scripts/lib/tts.cleanup.test.mjs6.6 KB
- 脚本audio/scripts/lib/tts.mjs17.8 KB
- 脚本audio/scripts/lib/tts.spawn.test.mjs5.1 KB
- 脚本audio/scripts/lib/tts.test.mjs8.7 KB
- 脚本audio/scripts/lib/voice-credit.mjs686 B
- 脚本audio/scripts/lib/voice-credit.test.mjs946 B
- 脚本audio/scripts/lyria-recipe.py4.9 KB
- 脚本audio/scripts/recording.test.mjs4.6 KB
- 脚本audio/scripts/wait-bgm.mjs5.7 KB
- 脚本audio/scripts/wait-bgm.test.mjs3.3 KB
- 参考文档luts/index.json2.0 KB
- 参考文档luts/README.md1.1 KB
- 参考文档references/audio.md3.0 KB
- 参考文档references/grading.md7.0 KB
- 参考文档references/heygen.md9.2 KB
- 参考文档references/local.md2.6 KB
- 参考文档references/media-treatment-recipes.md35.0 KB
- 参考文档references/media-treatments.md13.8 KB
- 参考文档references/memory.md3.7 KB
- 参考文档references/meta.md6.4 KB
- 参考文档references/mixing.md4.5 KB
- 参考文档references/operations.md15.7 KB
- 参考文档references/resolve.md9.9 KB
- 参考文档references/setup-providers.md9.1 KB
- 参考文档references/telemetry-dashboard.md4.1 KB
- 脚本scripts/audio-duck.mjs4.0 KB
- 脚本scripts/compatibility.test.mjs1.6 KB
- 脚本scripts/dither.mjs9.7 KB
- 脚本scripts/dither.test.mjs4.6 KB
- 脚本scripts/eval.mjs14.5 KB
- 脚本scripts/lib/config-lock.mjs1.5 KB
- 脚本scripts/lib/credit-limit.mjs2.0 KB
- 脚本scripts/lib/cutlist.mjs6.2 KB
- 脚本scripts/lib/duck.mjs3.8 KB
- 脚本scripts/lib/error-diffusion.mjs6.5 KB
- 脚本scripts/lib/index-gen.mjs1.9 KB
- 脚本scripts/lib/manifest.mjs9.2 KB
- 脚本scripts/lib/media-fetch.mjs2.8 KB
- 脚本scripts/lib/media-home.mjs730 B
- 脚本scripts/lib/npx-sync.mjs2.9 KB
- 脚本scripts/lib/parakeet-words.mjs1.1 KB
- 脚本scripts/lib/prefs-store.mjs6.8 KB
- 脚本scripts/lib/recipe-store.mjs13.0 KB
- 脚本scripts/lib/telemetry.mjs8.8 KB
- 脚本scripts/lib/telemetry.test.mjs3.0 KB
- 脚本scripts/lib/transcriptCutFade.mjs911 B
- 脚本scripts/lib/words.mjs728 B
- 脚本scripts/prefs.mjs2.3 KB
- 脚本scripts/recipe.mjs3.8 KB
- 脚本scripts/resolve-plugin.test.mjs2.5 KB
- 脚本scripts/resolve.mjs1.3 KB
- 脚本scripts/transcribe.mjs7.3 KB
- 脚本scripts/transcribe.test.mjs4.0 KB
- 脚本scripts/transcript-cut.mjs10.0 KB
- 脚本scripts/transcript-cut.test.mjs9.6 KB
03 SKILL.md 正文
Plugin installs: Inside a HyperFrames plugin, follow plugin execution rules.
Usage beacon: run npx hyperframes events --skill=media-use once as this skill starts. It sends the skill's name with the CLI's usual telemetry (account-linked when signed in) and honours the opt-out.
Media in HyperFrames
Media lands as a local file in the project's assets/ with a ledger record; renders never fetch. One verb finds or makes it:
npx hyperframes media-use resolve --type <type> --intent "<what you need>" --project <dir>
It prints one line, resolved <id> → <path> (<type>, <metadata>). List reusable assets first with --candidates and judge the fit yourself; reuse, ingest (--from) and adopt are in references/resolve.md.
Where it comes from
| Need | Free | HyperFrames credits | Local or the person's own key (only when they ask) |
|---|---|---|---|
Music (bgm) |
HeyGen catalog of 10k+ tracks (signed in) | Generated track | Local MusicGen |
Sound effects (sfx) |
HeyGen (signed in); Openverse (credit CC BY); bundled | ||
| Images, icons | HeyGen asset search, 75k+ (signed in) | Generated images | Local FLUX (mflux), if installed |
Logos (logo) |
theSVG, GitHub avatar, favicon; never redrawn | ||
Voiceover (voice) |
Voice Turbo, Free plan: 3 min a month | Voice Turbo on a paid plan, other HeyGen voices, cloning | npx hyperframes tts (Kokoro on device) |
| A presenter speaking | Avatar video (--type video) |
Local LTX for generic clips, if installed | |
| Transcripts | npx hyperframes transcribe (Parakeet or whisper) |
||
| Cutouts | Video: --type cutout |
npx hyperframes remove-background |
|
| Grades, LUTs, looks | npx hyperframes media-treatment |
Sign in. Every time a request needs a HeyGen model or the catalog, run npx hyperframes auth status first. Not signed in: tell the person in one line that sign-in is free and gives the music catalog, asset search and 3 min of Voice Turbo a month on the Free plan, ask them to type an exclamation mark and npx hyperframes auth login in the prompt, and wait until they say it is done. Use local tools only when the person asks, not as a fallback.
Host apps. Inside an app with its own media tools, use those first. When HEYGEN_API_BASE is set, the host pays: don't ask for a sign-in; relay a refused call's message as written and stop.
HeyGen. npx hyperframes media-use generate makes images, shots, talking photos, voices and music on the sign-in alone. Helpers and direct recipes need the heygen CLI; if it is missing, give the link and wait until they say it is installed. Direct heygen recipes bill that CLI's own login: use them only when that payer is selected.
Credits. Plan for the best result: no cheaper or free swaps, no dropped items, unless asked to save cost. Don't volunteer prices, estimates or usage; --plan is for you. A credit limit the person sets: write it once to .hyperframes/credit-limit.json as {"credits": N}; every paid call then refuses what would go past it, GPT Image only at estimate +10% (references/heygen.md) (--max-credits only tightens). A step that won't fit (a --plan over what is left, or a refused call): say what doesn't, ask before dropping or shrinking it. A refused call names a billing command: say why, ask them to run it, then retry.
Looks on real footage
Feedback that footage is dark, flat or dull, should feel retro or printed, needs a face hidden, or needs a reveal is media intent. Inspect the real <img>/<video>, pick one intent, and follow references/media-treatments.md; persist with npx hyperframes media-treatment, never a CSS, SVG or .cube stand-in.
Offer once, never add silently
Scan a piece you build or review once for concrete gaps (on-screen text with no voiceover, emoji standing in for icons, placeholder images, silent cuts, 10 s+ with no music, a colour cast) and offer the fixes in one ask. No signal, no suggestion; respect "leave it".
Where to look
| Task | Read |
|---|---|
| Resolve, reuse, adopt, ingest, flags | references/resolve.md |
Grading, LUTs, grade-compare |
references/grading.md |
| Voiceover, music, sound effects, captions, transcription | references/audio.md |
Cut, reframe or transform media; direct heygen recipes |
references/operations.md |
| Treatments, realtime effects, overlays, reveals | references/media-treatments.md |
Install, sign-in, credentials, --provider, --local-only, RAM ladders |
references/setup-providers.md |
media-use generate, HeyGen transcription, prices |
references/heygen.md |
| Fades, gain, ducking, automation, effects, buses on placed tracks | references/mixing.md |
| Local commands: grade, cutout, loudness, beats | references/local.md |
| Remembered preferences | references/memory.md |
04 同仓库更多 Skills
system-lifecycle-designer
Universal architectural methodology for designing granular, atomic, and sub-atomic lifecycles and end-to-end workflows for single functionality integrations across any domain (daemons, batch jobs, request transactions, resource pools). Provides patterns for deterministic identity, pre-commit validation, differential reconciliation, sticky leasing, state machines, transactional persistence, and closed-loop feedback.
style-sampling
Make a new episode in a proven video style - Collage Explainer, Finance Explainer, Animated Science Explainer, 3D Brand Explainer, 3D True Crime - on the person's topic. Use for "an episode of", "in the style of", "sample this style", 「用这个风格做一集」. One video to copy is reverse-any-video.
reverse-any-video
Rebuild any video file as an editable HyperFrames project - motion graphics, talking heads, live action or AI-generated footage - checked against the original frame by frame. Use to reverse, recreate, remake, replicate or copy a video, or 「复刻这个视频」「照着这个视频做一个」.
typescript-patterns
TypeScript patterns for strict, type-safe, maintainable code in modern TypeScript and JavaScript applications. Covers strict compiler configuration, type design, narrowing, discriminated unions, generics, async and error handling, module boundaries, dependency hygiene, and type-level testing. Use when writing or reviewing TypeScript or JavaScript code.
test-collaboration
Inventory and govern a project's test assets. Connect requirements, business rules, risks, bugs, and cross-boundary contracts to stable TEST-IDs and executable evidence in the repository's existing test registry or TESTS.md. Use for test inventory, test gap analysis, unit/integration/contract/E2E/smoke classification, bug-to-test regression protection, consumer/provider contract testing, test-necessity review, and pre-delivery evidence review.
story-lifecycle
Manage a file-based epic → story → sprint development loop without requiring an external project management tool. Creates and tracks epics, breaks them into user stories, assigns them to sprints, and drives implementation story by story. Use when starting a new feature initiative or when the team has no Jira/Linear/Taiga but needs structured delivery tracking.