Files
hyperframes/skills/hyperframes-media/scripts/lib/sfx.mjs
T
WaterrrForeverandClaude Opus 4.8 d0f0ec29e7 feat(skills): frame-preset library + shared audio engine (foundation) (#1632)
* feat(hyperframes-creative): add frame-preset library

Add a library of ready-made visual frame presets (claude, biennale-yellow,
blockframe, blue-professional, bold-poster, broadside, capsule, cartesian,
cobalt-grid, coral, creative-mode, daisy-days, editorial-forest, …), each with
a FRAME.md spec, a frame-showcase.html, and a per-preset caption-skin.html.
Registered in the creative design-spec so workflows can remix a preset onto
brand tokens.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(hyperframes-media): shared TTS/BGM/SFX audio engine

Add a shared audio engine under hyperframes-media (scripts/audio.mjs + lib/
tts.mjs, bgm.mjs, sfx.mjs, heygen.mjs) plus a bundled SFX pack and manifest.
Workflows resolve this engine by path (../../hyperframes-media/scripts/
audio.mjs) for text-to-speech, background music, and sound effects, so audio
is authored once and reused across skills instead of duplicated per workflow.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(skills): gate render on user review; refresh router, core, general-video

- hyperframes-cli: render is now user-gated — preview opens Studio (the timeline
  editor where the user can hand-edit anything, not just watch); never
  auto-render once checks pass, pause at preview and render only after approval.
- hyperframes (router): tighten the entry SKILL.md description + routing.
- hyperframes-core: rewrite SKILL.md and add script-format.md + storyboard-format.md
  references for the script-driven authoring architecture.
- general-video: tidy the fallback-workflow description and routing table.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* style(hyperframes-creative): reformat frame-preset showcase HTML

Run the HTML formatter over the frame-showcase.html files (indentation,
self-closing void tags, one CSS declaration per line). Formatting only — no
content or markup changes.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(hyperframes-media): correct wait-bgm field mapping and guard credential parse

Two correctness fixes from review (#1632):

- wait-bgm.mjs read audioMeta.bgm_path / audioMeta.bgm_enabled, but audio.mjs
  writes the path nested as bgm.path and the flag as bgm_pending. The detached
  generate path (Lyria/MusicGen) therefore always saw an empty path and exited
  status: disabled, silently dropping the music track even while generation was
  running. Read audioMeta.bgm?.path and gate on bgm_pending.
- heygenCredential() had an unguarded JSON.parse despite documenting that it
  never throws — a malformed ~/.heygen credentials file crashed the engine at
  startup instead of degrading to no-credential. Wrap the parse and return null.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* chore(hyperframes): add router tag to entry skill metadata

Fold the router metadata tag into the foundation rewrite of the entry SKILL.md.
This file is owned by this PR (the full router rewrite); keeping the tag tweak
here — instead of a separate edit on the pre-rewrite version in another PR —
avoids a guaranteed merge conflict between the two.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 22:49:10 +08:00

129 lines
4.6 KiB
JavaScript
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
// sfx.mjs — sound effects for the media audio engine. Provider-gated (NOT a
// per-cue merge): the decision is made once, by whether HeyGen is configured —
// mirroring how TTS and BGM degrade.
//
// HeyGen credential present → retrieve EVERY cue from HeyGen's audio library
// (/v3/audio/sounds, type=sound_effects, min_score=0.4). The bundled
// library is NOT consulted.
// HeyGen credential absent → resolve cues against the bundled 21-file
// library (assets/sfx/manifest.json), copying matched files into the
// project. Offline, deterministic, free.
//
// A cue that matches nothing is skipped (recorded as an anomaly); SFX never
// blocks a render. Every cue sits at volume ~0.35, under voice + BGM.
import { copyFileSync, existsSync, mkdirSync, readFileSync } from "node:fs";
import { join } from "node:path";
import { downloadTo, searchSounds } from "./heygen.mjs";
const SFX_VOLUME = 0.35;
const slug = (s) =>
s
.toLowerCase()
.replace(/[^a-z0-9]+/g, "-")
.replace(/^-+|-+$/g, "")
.slice(0, 40) || "x";
const r3 = (x) => Number(x.toFixed(3));
// cues: [{ id, name }] (id = the line/frame/scene the cue fires in). Returns
// { sfx: [{ id, name, file, source, offset_s, duration_s, volume }], anomalies }.
export async function resolveSfx({ cues, heygenOK, headers, hyperframesDir, sfxLibDir }) {
const sfx = [];
const anomalies = [];
const destDir = join(hyperframesDir, "assets", "sfx");
// Dedupe identical (id,name) cues — the same effect named twice in one line
// downloads/copies once.
const seen = new Set();
const uniq = cues.filter((c) => {
const k = `${c.id}:${c.name}`;
if (seen.has(k)) return false;
seen.add(k);
return true;
});
if (heygenOK) {
for (const { id, name } of uniq) {
try {
// SFX hits score low (~0.50.67), below the API's default 0.7 which
// silently drops most named cues — floor to 0.4. (BGM/music score high
// and keep the default.)
const results = await searchSounds(name, "sound_effects", headers, {
limit: 3,
minScore: 0.4,
});
if (!results.length) {
anomalies.push(`sfx "${name}" (id ${id}): no HeyGen match — skipped`);
continue;
}
const top = results[0];
const file = `assets/sfx/${slug(name)}.mp3`;
await downloadTo(top.audio_url, join(hyperframesDir, file));
sfx.push({
id,
name,
file,
source: "heygen",
offset_s: 0,
duration_s: typeof top.duration === "number" ? r3(top.duration) : 1.0,
volume: SFX_VOLUME,
});
} catch (e) {
anomalies.push(`sfx "${name}" (id ${id}): retrieval failed — ${e.message}`);
}
}
return { sfx, anomalies };
}
// ── offline: bundled library ──
const manifestPath = join(sfxLibDir, "manifest.json");
if (!existsSync(manifestPath)) {
if (uniq.length)
anomalies.push(`no HeyGen credential and no SFX library at ${sfxLibDir} — all cues dropped`);
return { sfx, anomalies };
}
let manifest;
try {
manifest = JSON.parse(readFileSync(manifestPath, "utf8"));
} catch (e) {
anomalies.push(`SFX manifest parse failed (${e.message}) — all cues dropped`);
return { sfx, anomalies };
}
// Build lookups: by manifest key, by file basename, and by slug of either, so
// a cue can name "whoosh", "whoosh.mp3", or "ui click" (→ slug match).
const byKey = new Map();
for (const [key, entry] of Object.entries(manifest)) {
if (!entry?.file || !isFinite(entry.duration)) continue;
const rec = { key, file: entry.file, duration: entry.duration };
byKey.set(key, rec);
byKey.set(entry.file, rec);
byKey.set(slug(key), rec);
byKey.set(slug(entry.file.replace(/\.\w+$/, "")), rec);
}
mkdirSync(destDir, { recursive: true });
for (const { id, name } of uniq) {
const hit = byKey.get(name) ?? byKey.get(slug(name));
if (!hit) {
const known = [...new Set([...byKey.values()].map((v) => v.key))].slice(0, 8).join(", ");
anomalies.push(
`sfx "${name}" (id ${id}): not in bundled library — skipped (have: ${known}…)`,
);
continue;
}
const src = join(sfxLibDir, hit.file);
const destRel = `assets/sfx/${hit.file}`;
const dest = join(hyperframesDir, destRel);
if (existsSync(src) && !existsSync(dest)) copyFileSync(src, dest);
sfx.push({
id,
name,
file: destRel,
source: "local",
offset_s: 0,
duration_s: r3(hit.duration),
volume: SFX_VOLUME,
});
}
return { sfx, anomalies };
}