feat(media-use): transcription (parakeet), transcript-cut, audio-duck editing tools

Author: miguel-heygen

skills-manifest.json

@@ -46,8 +46,8 @@
       "files": 10
     },
     "media-use": {
-      "hash": "4e07a35f60f1378e",
-      "files": 87
+      "hash": "21951022f0d7066f",
+      "files": 97
     },
     "motion-graphics": {
       "hash": "73771b2d1300236d",

skills/media-use/scripts/audio-duck.mjs

@@ -0,0 +1,121 @@
+#!/usr/bin/env node
+
+import { readFileSync } from "node:fs";
+import { resolve } from "node:path";
+import { parseArgs } from "node:util";
+import { duckKeyframes, speechSpans } from "./lib/duck.mjs";
+import { track } from "./lib/telemetry.mjs";
+
+const { values: args } = parseArgs({
+  options: {
+    meta: { type: "string" },
+    target: { type: "string" },
+    duck: { type: "string", default: "0.25" },
+    attack: { type: "string", default: "0.15" },
+    release: { type: "string", default: "0.4" },
+    "merge-gap": { type: "string", default: "0.6" },
+    sequential: { type: "boolean", default: false },
+    gap: { type: "string", default: "0" },
+    offsets: { type: "string" },
+    composition: { type: "string" },
+    json: { type: "boolean", default: false },
+    help: { type: "boolean", short: "h", default: false },
+  },
+  strict: true,
+});
+
+if (args.help) {
+  console.log(`media-use audio-duck — generate GSAP volume ducking keyframes
+
+Usage:
+  node audio-duck.mjs --meta audio_meta.json --target "#bgm"
+
+Options:
+  --meta          audio_meta.json or JSON word transcript
+  --target        GSAP selector for the background audio element
+  --duck          Duck multiplier (default: 0.25)
+  --attack        Duck-in duration seconds (default: 0.15)
+  --release       Restore duration seconds (default: 0.4)
+  --merge-gap     Bridge speech gaps smaller than this many seconds (default: 0.6)
+  --sequential    Place multi-line meta back to back at composition time
+  --gap           Extra seconds between sequential lines (default: 0)
+  --offsets       Explicit placement, "l1=0,l2=3.4" (voice id = start seconds)
+  --composition   Read target data-volume from this HTML file
+  --json          Output { spans, keyframes }
+  --help, -h      Show this help`);
+  process.exit(0);
+}
+
+try {
+  run();
+  await track("media_use_duck", { sequential: !!args.sequential });
+} catch (err) {
+  if (args.json) console.log(JSON.stringify({ ok: false, error: err.message }));
+  else console.error(`error: ${err.message}`);
+  process.exit(1);
+}
+
+function run() {
+  if (!args.meta || !args.target) throw new Error("--meta and --target are required");
+  const meta = JSON.parse(readFileSync(resolve(args.meta), "utf8"));
+  const target = args.target;
+  const baseVolume = readBaseVolume(args.composition, target);
+  const offsets = args.offsets
+    ? Object.fromEntries(
+        args.offsets.split(",").map((pair) => {
+          const [id, t] = pair.split("=");
+          return [id.trim(), Number(t)];
+        }),
+      )
+    : undefined;
+  const spans = speechSpans(meta, {
+    mergeGap: Number(args["merge-gap"]),
+    sequential: args.sequential,
+    gap: Number(args.gap),
+    offsets,
+  });
+  const keyframes = duckKeyframes(spans, {
+    duck: Number(args.duck),
+    attack: Number(args.attack),
+    release: Number(args.release),
+    baseVolume,
+  });
+
+  if (args.json) {
+    console.log(JSON.stringify({ spans, keyframes }));
+    return;
+  }
+
+  console.log(
+    `// auto-duck: ${target} under narration (generated; base volume ${fmt(baseVolume)})`,
+  );
+  for (const keyframe of keyframes) {
+    console.log(
+      `tl.to(${JSON.stringify(target)}, { volume: ${fmt(keyframe.volume)}, duration: ${fmt(
+        keyframe.duration,
+      )} }, ${fmt(keyframe.time)});`,
+    );
+  }
+}
+
+function readBaseVolume(composition, target) {
+  if (!composition || !target.startsWith("#")) return 1;
+  const id = target.slice(1);
+  const html = readFileSync(resolve(composition), "utf8");
+  // ponytail: regex is enough here because this only reads one attribute from
+  // one user-authored composition element, not arbitrary HTML.
+  const tag = html.match(new RegExp(`<[^>]*\\bid=["']${escapeRegExp(id)}["'][^>]*>`, "i"))?.[0];
+  const raw = tag?.match(/\bdata-volume=["']([^"']+)["']/i)?.[1];
+  const volume = Number(raw);
+  return Number.isFinite(volume) ? volume : 1;
+}
+
+function escapeRegExp(value) {
+  return value.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
+}
+
+function fmt(n) {
+  return Number(n)
+    .toFixed(3)
+    .replace(/\.?0+$/, "");
+}

skills/media-use/scripts/lib/coverage.test.mjs

@@ -0,0 +1,112 @@
+import { strict as assert } from "node:assert";
+import { test } from "node:test";
+import { existsSync } from "node:fs";
+import { join, dirname } from "node:path";
+import { fileURLToPath } from "node:url";
+import { listTypes, getProviders } from "./registry.mjs";
+import { CAPABILITIES, listModels } from "./local-models.mjs";
+
+// Capstone: media-use must actually OWN each hyperframes media weakness. This
+// test enforces the weakness→owner matrix in SKILL.md so a claim can't rot — if
+// a capability's entrypoint disappears, this fails.
+
+const SKILL = join(dirname(fileURLToPath(import.meta.url)), "..", "..");
+
+test("weakness: audio-only → media-use resolves image + icon", () => {
+  for (const t of ["image", "icon"]) {
+    assert.ok(getProviders(t).length > 0, `no provider for ${t}`);
+  }
+});
+
+test("weakness: no voice/audio gen → media-use exposes voice + the audio engine", () => {
+  assert.ok(listTypes().includes("voice"), "voice type missing");
+  assert.ok(getProviders("voice").length > 0, "no enabled voice provider (Bin approved)");
+  assert.ok(existsSync(join(SKILL, "audio", "scripts", "audio.mjs")), "audio engine missing");
+});
+
+test("weakness: scattered audio engine → consolidated under media-use (hyperframes-media gone)", () => {
+  assert.ok(existsSync(join(SKILL, "audio", "scripts", "lib", "tts.mjs")), "tts engine missing");
+  assert.ok(
+    existsSync(join(SKILL, "audio", "assets", "sfx", "manifest.json")),
+    "bundled SFX missing",
+  );
+});
+
+test("weakness: no media-ops → ops guidance reference exists", () => {
+  assert.ok(existsSync(join(SKILL, "references", "operations.md")), "operations.md missing");
+});
+
+test("weakness: no transcript-driven cutting → cut compiler entrypoints exist", async () => {
+  assert.ok(existsSync(join(SKILL, "scripts", "transcript-cut.mjs")), "transcript-cut missing");
+  assert.ok(existsSync(join(SKILL, "scripts", "lib", "cutlist.mjs")), "cutlist lib missing");
+  const cutlist = await import("./cutlist.mjs");
+  assert.equal(typeof cutlist.compileCutList, "function");
+});
+
+test("weakness: whisper.cpp is weak → better local ASR (Parakeet) entrypoint exists", async () => {
+  assert.ok(existsSync(join(SKILL, "scripts", "transcribe.mjs")), "transcribe.mjs missing");
+  const pw = await import("./parakeet-words.mjs");
+  assert.equal(typeof pw.mergeTokensToWords, "function", "token->word merge missing");
+  const lm = await import("./local-models.mjs");
+  const asr = lm.listModels("asr");
+  const parakeet = asr.find((m) => m.id === "parakeet-mlx");
+  assert.ok(parakeet && parakeet.rank === 0, "Parakeet must be the rank-0 preferred ASR");
+});
+
+test("weakness: no auto-duck/loudness → duck compiler and recipes exist", async () => {
+  assert.ok(existsSync(join(SKILL, "scripts", "audio-duck.mjs")), "audio-duck missing");
+  assert.ok(existsSync(join(SKILL, "scripts", "lib", "duck.mjs")), "duck lib missing");
+  assert.ok(existsSync(join(SKILL, "references", "operations.md")), "operations.md missing");
+  const duck = await import("./duck.mjs");
+  assert.equal(typeof duck.speechSpans, "function");
+  assert.equal(typeof duck.duckKeyframes, "function");
+});
+
+test("weakness: no cross-project memory → global cache + ingest entrypoints exist", async () => {
+  const cache = await import("./cache.mjs");
+  assert.equal(typeof cache.cachePut, "function");
+  assert.equal(typeof cache.promote, "function");
+  assert.equal(typeof cache.globalMediaDir, "function");
+  const freeze = await import("./freeze.mjs");
+  assert.equal(typeof freeze.isDirectMediaUrl, "function", "ingest URL guard missing");
+});
+
+// Wenbo (06-29): heygen free-usage is the default; local models are the opt-out
+// fallback ("if user no, then local"). We still assert the fallback table is
+// populated so the opt-out path stays real.
+test("weakness: weak local defaults → local models exist as the opt-out fallback (tts/asr/upscale)", () => {
+  for (const cap of ["tts", "asr", "upscale"]) {
+    assert.ok(CAPABILITIES.includes(cap), `capability ${cap} missing`);
+    assert.ok(listModels(cap).length > 0, `no local models for ${cap}`);
+  }
+});
+
+test("weakness: no image generation → local mflux (RAM-graded) + codex upsell", async () => {
+  const ps = getProviders("image");
+  assert.ok(
+    ps.some((p) => p.name === "mflux.local" && typeof p.generate === "function"),
+    "local image gen missing",
+  );
+  assert.ok(
+    ps.some((p) => p.name === "codex.image_gen" && typeof p.generate === "function"),
+    "codex image upsell missing",
+  );
+  const lm = await import("./local-models.mjs");
+  assert.ok(lm.CAPABILITIES.includes("imagegen"), "imagegen capability missing");
+  assert.ok(lm.listModels("imagegen").length >= 3, "imagegen RAM ladder too small");
+  assert.equal(typeof lm.describeModelLadder, "function", "agent-facing ladder missing");
+});
+
+test("weakness: no video generation → local videogen ladder + heygen avatar upsell", async () => {
+  const lm = await import("./local-models.mjs");
+  assert.ok(lm.CAPABILITIES.includes("videogen"), "videogen capability missing");
+  assert.ok(lm.listModels("videogen").length >= 2, "videogen ladder too small");
+  const ops = existsSync(join(SKILL, "references", "operations.md"));
+  assert.ok(ops, "operations.md (avatar-upsell recipe) missing");
+});
+
+test("every resolve type has at least one enabled provider", () => {
+  for (const t of listTypes()) {
+    assert.ok(getProviders(t).length > 0, `type ${t} has no enabled provider`);
+  }
+});