Home / All Skills / Content & Media Creation / real-sound
English (EN)简体中文 (ZH)日本語 (JA)
Content & Media Creation · Leonxlnx/earshot

real-sound

Build premium, realistic soundtracks for code-made videos and animations from real licensed recordings - launch films, product and feature videos, UI walkthroughs, logo stings, explainers, trailers and animated shorts made with Remotion, HyperFrames, three.js, GSAP or any renderer. Use this whenever a video or animation needs sound design, SFX, foley, ambience, music, a soundtrack, a score, UI click / whoosh / riser / impact / logo-sting sounds, or a music edit to picture; whenever a synthesized or "random" sounding soundtrack must be replaced with real recordings; or when the user asks to source, license, credit, mix, master, critique or mux audio for a film. It covers cue lists from the picture, sourcing from Freesound / Mixkit / composer libraries with licence checks, a music edit at bar lines, a JSON sound design rendered by a deterministic mixer, measured QA (clicks, masking, harshness, sync, loudness) plus earshot listening, a multi-agent critique, mastering, credits and the mux.

L4 High-Privilege · Graded auth & full auditV1 Commit-PinnedExecute CommandNetwork AccessWrite FileDual-pass Audit
Author LeonxlnxGitHub Leonxlnx/earshot ↗Stars 2772License MITCommit 591fa3e028
Control levels describe skill capabilities and suggested control measures; they do not represent quality or safety certifications, nor do they dictate usability. Usage decisions rest entirely with users and administrators. Different agent hosts apply varying constraints; do not assume hosts provide automatic protection. Third-party skill copyrights belong to their original authors. Use at your own risk.

1How It Works & Mechanism

Precise audio-visual alignment driven by deterministic mixing and code: placing licensed real audio onto cue frames computed from video frames

skills/real-sound/SKILL.md
The soundtrack is built ONLY from real, professionally recorded or produced audio (one licensed music track, real foley and SFX, real ambiences), placed on the picture's cue frames by a deterministic mixer, measured instead of listened to, critiqued through five lenses, fixed by one agent, mastered, credited and muxed.
Strictly adheres to a code-driven mixing pipeline, where code handles sequencing and mastering

Polite scraping of high-quality audio assets from open audio libraries (Freesound / Mixkit) with strict license audits

skills/real-sound/SKILL.md
Freesound (CC0 / CC BY; HQ preview `cdn.freesound.org/previews/<id//1000>/<id>_<user>-hq.ogg`), Mixkit (WAV `assets.mixkit.co/active_storage/sfx/<id>/<id>.wav`), composer libraries for music; licences read on each item's own page (`references/licences.md`); polite sequential downloads; every file measured:
Explicitly specifies download sources, download rate limits, and license compliance requirements

A 10-step end-to-end production pipeline: from frame-accurate cue lists and concept briefs to multi-pass parallel design fragments, final mastering, and multiplexing

skills/real-sound/SKILL.md
| 0. cue list | lead | `out/cues.json` | sync frames computed from the picture code | | 1. brief | lead | `audio/SOUND_BRIEF.md` | every cue has a sound need (or "nothing") | | 2. sourcing (per category, parallel) | sourcing agents | `audio/assets/<cat>/`, manifests | each file measured + earshot `realness` "real or pro-produced" on the trim used (an "uncertain" only with its evidence and a trim-level re-check written in the manifest) | | 3. licence audit | auditor | `audit.json` | `audit.py` exit 0 for what the film uses | | 4. music edit | music supervisor | `audio/design/music.json` | grid verified, drop on the reveal, splices clean | | 5. design fragments (per category, parallel) | designers | `audio/design/<cat>.json` | solo render + qa clean | | 6. integrate | lead | soundtrack, stems, report, trace | master gate (+-0.5 LU, <= -1.5 dBTP) | | 7. QA + listening | lead | `out/qa/qa.json`, earshot timeline / sheet / critique | no qa fail | | 8. critique (5 lenses, parallel, read-only) | critics | ranked issues + tested operations | | | 9. fix | ONE fixer | the design | qa: no regression | | 10. master, credits, mux | lead | `CREDITS.md`, description text, the film | credits exit 0, lag 0 |
Multi-agent collaboration with strict step-by-step QA gates

2Core Capabilities

01Real acoustic asset retrieval and license compliance auditing
02Deterministic multitrack arrangement and mixing of SFX and background music
03Audio-video sync QA, mastering, and final media multiplexing (mux)

3External Dependencies

KindDependency / Endpoint
networkFreesound CDN
networkMixkit SFX

4Recommended Governance & Evidence

Suggested Controls for Safe Operation
For Agent Runtime
Graded/per-use authorization, sandbox recommended
For Administrators
Approval workflow, rollback support, full audit
Evidence & Triggers (File Paths & Excerpts)
  • scripts/: Executes Python mixing and mastering scripts (analyze.py, mix.py, master.py, qa.py, etc.) and mux.mjs
  • 网络端点: Sequentially fetches audio preview assets from cdn.freesound.org and assets.mixkit.co
  • 本地工作目录: Generates audio/ assets, stem files, mastered WAV files, and CREDITS.md locally
Audit Notes: Local script execution and external asset retrieval: relies on a local Python scientific stack and ffmpeg for audio engineering, downloads assets from public platforms such as Freesound, and performs extensive local filesystem writes and master rendering.

5Second-Pass Verification

  • [ok] 依赖与脚本扫描 — 10 个脚本纯本地科学计算与 ffmpeg 调度，无隐藏混淆内容
  • [ok] 素材源合规性 — 仅访问 Freesound/Mixkit 公开预览端点，强制附带 licenses 审计与声明

6Verdict & Scenarios

  • True professional cinematic audio-visual alignment workflow, featuring independent 5-perspective critiques and automated QA gates
  • Outputs not only the mastered audio but also automatically generates a comprehensive license manifest (CREDITS.md)
    • Best for: Developers using code-based video tools like Remotion, HyperFrames, and GSAP looking to add high-fidelity sound design to product launch films
    Not for: Minimal static graphics or slideshows that only need generic, random background music without frame-accurate sync
    Install Agent-Ready
    ① Verified Mirror 2026-10-25
    Option A · Direct DownloadDownload real-sound.tar.gz
    sha256: b7b5c34dfba6fd2c…
    Option B · Copy Guide for Agent
    install.json
    Agents automatically download and verify mirrors from this JSON guide.
    ② Upstream GitHub
    GitHub Repo ↗
    Pinned to commit 591fa3e028.