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

skills-manifest.json

@@ -46,8 +46,8 @@
       "files": 10
     },
     "media-use": {
-      "hash": "969e6ed350111d63",
+      "hash": "db5787c5ff2bd852",
-      "files": 87
+      "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`);
+  }
+});

skills/media-use/scripts/lib/cutlist.mjs

@@ -0,0 +1,184 @@
+import { normalizeWords } from "./words.mjs";
+
+const MIN_SEGMENT_SECONDS = 0.2;
+const SILENCE_PAD_SECONDS = 0.15;
+
+export function compileCutList(transcript, opts = {}) {
+  const words = normalizeWords(transcript);
+  if (opts.keep != null && hasRemovalSource(opts)) {
+    throw new Error("--keep is mutually exclusive with removal options");
+  }
+
+  if (opts.keep != null) {
+    const duration = durationFrom(words, opts);
+    const ranges = parseTimeRanges(opts.keep);
+    return finalizeKept(duration != null ? clampRanges(ranges, duration) : ranges);
+  }
+
+  const duration = durationFrom(words, opts);
+  if (!duration) return [];
+
+  const removals = [
+    ...parseTimeRanges(opts.remove),
+    ...wordIndexRanges(words, opts.removeWords),
+    ...fillerRanges(words, opts.removeFillers),
+    ...silenceRanges(words, opts.cutSilence),
+  ];
+  const mergedRemovals = mergeRanges(clampRanges(removals, duration));
+  return finalizeKept(invertRanges(mergedRemovals, duration));
+}
+
+function hasRemovalSource(opts) {
+  return (
+    opts.remove != null ||
+    opts.removeWords != null ||
+    opts.removeFillers != null ||
+    opts.cutSilence != null
+  );
+}
+
+function durationFrom(words, opts) {
+  const explicit = Number(opts.duration ?? opts.totalDuration);
+  if (Number.isFinite(explicit) && explicit > 0) return explicit;
+  const last = words.at(-1);
+  return last && Number.isFinite(last.end) && last.end > 0 ? last.end : null;
+}
+
+function parseTimeRanges(value) {
+  if (value == null || value === false || value === "") return [];
+  if (typeof value === "string") {
+    return value
+      .split(",")
+      .map((part) => part.trim())
+      .filter(Boolean)
+      .map(parseRangeString);
+  }
+  if (!Array.isArray(value)) throw new Error("range list must be a string or array");
+  return value.map((range) => {
+    if (Array.isArray(range)) return cleanRange(Number(range[0]), Number(range[1]));
+    return cleanRange(Number(range?.start), Number(range?.end));
+  });
+}
+
+function parseRangeString(value) {
+  const match = value.match(/^([0-9]*\.?[0-9]+)\s*-\s*([0-9]*\.?[0-9]+)$/);
+  if (!match) throw new Error(`invalid range: ${value}`);
+  return cleanRange(Number(match[1]), Number(match[2]));
+}
+
+function cleanRange(start, end) {
+  if (!Number.isFinite(start) || !Number.isFinite(end)) {
+    throw new Error("range start/end must be finite numbers");
+  }
+  if (end < start) throw new Error(`range end ${end} is before start ${start}`);
+  return { start, end };
+}
+
+function wordIndexRanges(words, value) {
+  if (value == null || value === false || value === "") return [];
+  const ranges = typeof value === "string" ? value.split(",") : value;
+  if (!Array.isArray(ranges)) throw new Error("--remove-words must be a string or array");
+  return ranges
+    .map((range) => (typeof range === "string" ? range.trim() : range))
+    .filter(Boolean)
+    .map((range) => {
+      const [first, last = first] =
+        typeof range === "string" ? range.split("-").map((n) => n.trim()) : range;
+      const startIndex = Number(first);
+      const endIndex = Number(last);
+      if (!Number.isInteger(startIndex) || !Number.isInteger(endIndex)) {
+        throw new Error(`invalid word range: ${range}`);
+      }
+      if (startIndex < 0 || endIndex < startIndex || endIndex >= words.length) {
+        throw new Error(`word range out of bounds: ${range}`);
+      }
+      return { start: words[startIndex].start, end: words[endIndex].end };
+    });
+}
+
+function fillerRanges(words, value) {
+  if (value == null || value === false || value === "") return [];
+  const fillers = Array.isArray(value)
+    ? value
+    : String(value)
+        .split(",")
+        .map((s) => s.trim());
+  const set = new Set(fillers.filter(Boolean).map(bareToken));
+  if (set.size === 0) return [];
+  // Whisper emits words with attached punctuation and arbitrary case
+  // ("UM," / "Um."), so compare bare tokens.
+  return words
+    .filter((word) => set.has(bareToken(word.text)))
+    .map((word) => ({ start: word.start, end: word.end }));
+}
+
+function bareToken(text) {
+  return String(text)
+    .toLowerCase()
+    .replace(/^[^\p{L}\p{N}]+|[^\p{L}\p{N}]+$/gu, "");
+}
+
+function silenceRanges(words, value) {
+  if (value == null || value === false || value === "") return [];
+  const threshold = Number(value);
+  if (!Number.isFinite(threshold) || threshold <= 0) {
+    throw new Error("--cut-silence must be a positive number");
+  }
+  const ranges = [];
+  for (let i = 0; i < words.length - 1; i++) {
+    const current = words[i];
+    const next = words[i + 1];
+    const gap = next.start - current.end;
+    if (gap <= threshold) continue;
+    const start = current.end + SILENCE_PAD_SECONDS;
+    const end = next.start - SILENCE_PAD_SECONDS;
+    if (end > start) ranges.push({ start, end });
+  }
+  return ranges;
+}
+
+function clampRanges(ranges, duration) {
+  return ranges
+    .map((range) => ({
+      start: Math.max(0, Math.min(duration, range.start)),
+      end: Math.max(0, Math.min(duration, range.end)),
+    }))
+    .filter((range) => range.end > range.start);
+}
+
+function mergeRanges(ranges) {
+  const sorted = ranges
+    .map((range) => ({ start: round3(range.start), end: round3(range.end) }))
+    .sort((a, b) => a.start - b.start || a.end - b.end);
+  const merged = [];
+  for (const range of sorted) {
+    const prev = merged.at(-1);
+    if (prev && range.start <= prev.end) {
+      prev.end = Math.max(prev.end, range.end);
+    } else {
+      merged.push({ ...range });
+    }
+  }
+  return merged;
+}
+
+function invertRanges(removals, duration) {
+  const kept = [];
+  let cursor = 0;
+  for (const range of removals) {
+    if (range.start > cursor) kept.push({ start: cursor, end: range.start });
+    cursor = Math.max(cursor, range.end);
+  }
+  if (cursor < duration) kept.push({ start: cursor, end: duration });
+  return kept;
+}
+
+function finalizeKept(ranges) {
+  return mergeRanges(ranges)
+    .map((range) => ({ start: round3(range.start), end: round3(range.end) }))
+    .filter((range) => round3(range.end - range.start) >= MIN_SEGMENT_SECONDS);
+}
+
+function round3(n) {
+  return Math.round(Number(n) * 1000) / 1000;
+}

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

@@ -0,0 +1,148 @@
+import { strict as assert } from "node:assert";
+import { execFileSync } from "node:child_process";
+import { mkdtempSync, writeFileSync, rmSync } from "node:fs";
+import { join, dirname } from "node:path";
+import { tmpdir } from "node:os";
+import { fileURLToPath } from "node:url";
+import { test } from "node:test";
+import { compileCutList } from "./cutlist.mjs";
+
+const HERE = dirname(fileURLToPath(import.meta.url));
+const SCRIPT = join(HERE, "..", "transcript-cut.mjs");
+
+test("explicit --remove ranges invert to kept segments", () => {
+  const transcript = [
+    word("w0", "alpha", 0, 1),
+    word("w1", "beta", 1.2, 2),
+    word("w2", "gamma", 2.2, 5),
+  ];
+
+  assert.deepEqual(compileCutList(transcript, { remove: "1-2.5" }), [
+    { start: 0, end: 1 },
+    { start: 2.5, end: 5 },
+  ]);
+});
+
+test("--remove-words resolves inclusive word-index ranges to time ranges", () => {
+  const transcript = [
+    word("w0", "zero", 0, 0.5),
+    word("w1", "one", 0.6, 1),
+    word("w2", "two", 1.1, 1.5),
+    word("w3", "three", 2, 3),
+  ];
+
+  assert.deepEqual(compileCutList(transcript, { removeWords: "1-2" }), [
+    { start: 0, end: 0.6 },
+    { start: 1.5, end: 3 },
+  ]);
+});
+
+test("--remove-fillers drops case-insensitive matching words", () => {
+  const transcript = [
+    word("w0", "Hello", 0, 0.5),
+    word("w1", "Um", 0.5, 0.7),
+    word("w2", "world", 0.8, 1.2),
+    word("w3", "LIKE", 1.3, 1.5),
+    word("w4", "done", 1.6, 2),
+  ];
+
+  assert.deepEqual(compileCutList(transcript, { removeFillers: "um,like" }), [
+    { start: 0, end: 0.5 },
+    { start: 0.7, end: 1.3 },
+    { start: 1.5, end: 2 },
+  ]);
+});
+
+test("--cut-silence removes only the center of long inter-word gaps", () => {
+  const transcript = [word("w0", "a", 0, 0.5), word("w1", "b", 2, 2.5), word("w2", "c", 2.7, 3)];
+
+  assert.deepEqual(compileCutList(transcript, { cutSilence: 0.8 }), [
+    { start: 0, end: 0.65 },
+    { start: 1.85, end: 3 },
+  ]);
+});
+
+test("overlapping removal sources merge before inversion", () => {
+  const transcript = [
+    word("w0", "start", 0, 0.5),
+    word("w1", "um", 0.9, 1.1),
+    word("w2", "middle", 2.5, 2.8),
+    word("w3", "more", 3.1, 3.4),
+    word("w4", "end", 5.5, 6),
+  ];
+
+  assert.deepEqual(
+    compileCutList(transcript, {
+      remove: "1-2.7",
+      removeWords: "2-3",
+      removeFillers: "um",
+    }),
+    [
+      { start: 0, end: 0.9 },
+      { start: 3.4, end: 6 },
+    ],
+  );
+});
+
+test("kept slivers shorter than 0.2s are dropped", () => {
+  const transcript = [word("w0", "start", 0, 0.5), word("w1", "end", 2.5, 3)];
+
+  assert.deepEqual(compileCutList(transcript, { remove: "0.1-2.95" }), []);
+});
+
+test("--keep is inverse mode and coalesces direct kept ranges", () => {
+  const transcript = [word("w0", "start", 0, 0.5), word("w1", "end", 4.5, 5)];
+
+  assert.deepEqual(compileCutList(transcript, { keep: "3-4,1-2,1.5-2.5,4.1-4.2" }), [
+    { start: 1, end: 2.5 },
+    { start: 3, end: 4 },
+  ]);
+});
+
+test("--plan on a fixture transcript prints the exact segment JSON", () => {
+  const dir = mkdtempSync(join(tmpdir(), "media-use-cutlist-"));
+  try {
+    const transcriptPath = join(dir, "fixture.json");
+    writeFileSync(
+      transcriptPath,
+      JSON.stringify([
+        word("w0", "hello", 0, 0.4),
+        word("w1", "um", 0.5, 0.65),
+        word("w2", "there", 0.7, 1),
+        word("w3", "pause", 2.2, 2.5),
+        word("w4", "end", 2.7, 3.2),
+      ]),
+    );
+
+    const out = execFileSync(
+      process.execPath,
+      [
+        SCRIPT,
+        "--input",
+        "ignored.mp4",
+        "--transcript",
+        transcriptPath,
+        "--remove",
+        "0.9-1.2",
+        "--remove-fillers",
+        "um",
+        "--cut-silence",
+        "0.8",
+        "--plan",
+      ],
+      { encoding: "utf8" },
+    );
+
+    assert.deepEqual(JSON.parse(out), [
+      { start: 0, end: 0.5 },
+      { start: 0.65, end: 0.9 },
+      { start: 2.05, end: 3.2 },
+    ]);
+  } finally {
+    rmSync(dir, { recursive: true, force: true });
+  }
+});
+
+function word(id, text, start, end) {
+  return { id, text, start, end };
+}

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

@@ -0,0 +1,89 @@
+import { wordListsFromMediaMeta } from "./words.mjs";
+
+/**
+ * Speech spans from word timestamps.
+ *
+ * audio_meta.json word times are relative to EACH LINE'S OWN FILE, not to the
+ * composition. Without placement info, multiple lines would overlap at t=0 and
+ * merge into one bogus span. Placement options:
+ *   offsets:    { [voiceId]: startSeconds } explicit composition placement
+ *   sequential: stack lines back to back (plus `gap` seconds between lines)
+ * A single word list (bare transcript) needs neither.
+ */
+export function speechSpans(meta, { mergeGap = 0.6, offsets, sequential = false, gap = 0 } = {}) {
+  const merge = Number(mergeGap);
+  const lists = wordListsFromMediaMeta(meta);
+  const voices = Array.isArray(meta?.voices) ? meta.voices : [];
+  if (lists.length > 1 && !offsets && !sequential) {
+    throw new Error(
+      "audio_meta has multiple voice lines with file-relative times; pass --sequential or --offsets so spans land at composition time",
+    );
+  }
+  const intervals = [];
+  let cursor = 0;
+  for (let i = 0; i < lists.length; i++) {
+    const voice = voices[i];
+    let offset = 0;
+    if (offsets) {
+      const id = voice?.id ?? String(i);
+      if (!(id in offsets)) throw new Error(`--offsets is missing voice "${id}"`);
+      offset = Number(offsets[id]) || 0;
+    } else if (sequential) {
+      offset = cursor;
+      const lineDuration = Number(voice?.duration_s) || Math.max(...lists[i].map((w) => w.end), 0);
+      cursor += lineDuration + (Number(gap) || 0);
+    }
+    for (const word of lists[i]) {
+      if (word.end > word.start)
+        intervals.push({ start: word.start + offset, end: word.end + offset });
+    }
+  }
+  return mergeIntervals(intervals, Number.isFinite(merge) && merge >= 0 ? merge : 0.6);
+}
+
+export function duckKeyframes(
+  spans,
+  { duck = 0.25, attack = 0.15, release = 0.4, baseVolume = 1 } = {},
+) {
+  const base = finiteOr(baseVolume, 1);
+  const ducked = round3(base * finiteOr(duck, 0.25));
+  const keyframes = [];
+  for (const span of spans) {
+    keyframes.push({
+      time: round3(Math.max(0, finiteOr(span.start, 0))),
+      volume: ducked,
+      duration: round3(finiteOr(attack, 0.15)),
+    });
+    keyframes.push({
+      time: round3(Math.max(0, finiteOr(span.end, 0))),
+      volume: round3(base),
+      duration: round3(finiteOr(release, 0.4)),
+    });
+  }
+  return keyframes.sort((a, b) => a.time - b.time);
+}
+
+function mergeIntervals(intervals, mergeGap) {
+  const sorted = intervals
+    .map((range) => ({ start: round3(range.start), end: round3(range.end) }))
+    .sort((a, b) => a.start - b.start || a.end - b.end);
+  const merged = [];
+  for (const range of sorted) {
+    const prev = merged.at(-1);
+    if (prev && (range.start <= prev.end || range.start - prev.end < mergeGap)) {
+      prev.end = Math.max(prev.end, range.end);
+    } else {
+      merged.push({ ...range });
+    }
+  }
+  return merged;
+}
+
+function finiteOr(value, fallback) {
+  const n = Number(value);
+  return Number.isFinite(n) ? n : fallback;
+}
+
+function round3(n) {
+  return Math.round(Number(n) * 1000) / 1000;
+}

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

@@ -0,0 +1,118 @@
+import { strict as assert } from "node:assert";
+import { execFileSync } from "node:child_process";
+import { mkdtempSync, writeFileSync, rmSync } from "node:fs";
+import { join, dirname } from "node:path";
+import { tmpdir } from "node:os";
+import { fileURLToPath } from "node:url";
+import { test } from "node:test";
+import { duckKeyframes, speechSpans } from "./duck.mjs";
+
+const HERE = dirname(fileURLToPath(import.meta.url));
+const SCRIPT = join(HERE, "..", "audio-duck.mjs");
+
+test("speechSpans bridges gaps smaller than mergeGap", () => {
+  const meta = {
+    words: [word("w0", "one", 0, 0.5), word("w1", "two", 0.8, 1), word("w2", "three", 2, 2.2)],
+  };
+
+  assert.deepEqual(speechSpans(meta, { mergeGap: 0.4 }), [
+    { start: 0, end: 1 },
+    { start: 2, end: 2.2 },
+  ]);
+});
+
+test("speechSpans refuses multi-line meta without placement (file-relative times)", () => {
+  const meta = {
+    voices: [
+      { id: "a", words: [word("w0", "one", 0, 1)] },
+      { id: "b", words: [word("w1", "two", 0, 1)] },
+    ],
+  };
+  assert.throws(() => speechSpans(meta, { mergeGap: 0.2 }), /--sequential or --offsets/);
+});
+
+test("speechSpans sequential stacks lines by duration plus gap", () => {
+  const meta = {
+    voices: [
+      { id: "a", duration_s: 2, words: [word("w0", "one", 0.1, 1.9)] },
+      { id: "b", duration_s: 1, words: [word("w1", "two", 0.1, 0.9)] },
+    ],
+  };
+  assert.deepEqual(speechSpans(meta, { mergeGap: 0.2, sequential: true, gap: 0.5 }), [
+    { start: 0.1, end: 1.9 },
+    { start: 2.6, end: 3.4 },
+  ]);
+});
+
+test("speechSpans explicit offsets place each line at composition time", () => {
+  const meta = {
+    voices: [
+      { id: "a", words: [word("w0", "one", 0, 1)] },
+      { id: "b", words: [word("w1", "two", 0, 1)] },
+    ],
+  };
+  assert.deepEqual(speechSpans(meta, { mergeGap: 0.2, offsets: { a: 0, b: 4 } }), [
+    { start: 0, end: 1 },
+    { start: 4, end: 5 },
+  ]);
+  assert.throws(() => speechSpans(meta, { offsets: { a: 0 } }), /missing voice "b"/);
+});
+
+test("speechSpans returns empty spans for empty input", () => {
+  assert.deepEqual(speechSpans({ voices: [] }, { mergeGap: 0.6 }), []);
+});
+
+test("duckKeyframes shapes attack and release from base volume", () => {
+  assert.deepEqual(
+    duckKeyframes([{ start: 3, end: 5 }], {
+      duck: 0.25,
+      attack: 0.15,
+      release: 0.4,
+      baseVolume: 0.6,
+    }),
+    [
+      { time: 3, volume: 0.15, duration: 0.15 },
+      { time: 5, volume: 0.6, duration: 0.4 },
+    ],
+  );
+});
+
+test("--json spans match --merge-gap semantics exactly", () => {
+  const dir = mkdtempSync(join(tmpdir(), "media-use-duck-"));
+  try {
+    const metaPath = join(dir, "audio_meta.json");
+    writeFileSync(
+      metaPath,
+      JSON.stringify({
+        voices: [
+          {
+            id: "narration",
+            words: [
+              word("w0", "one", 0, 0.4),
+              word("w1", "two", 0.9, 1.2),
+              word("w2", "three", 1.8, 2.1),
+            ],
+          },
+        ],
+      }),
+    );
+
+    const out = execFileSync(
+      process.execPath,
+      [SCRIPT, "--meta", metaPath, "--target", "#bgm", "--merge-gap", "0.6", "--json"],
+      { encoding: "utf8" },
+    );
+
+    const parsed = JSON.parse(out);
+    assert.deepEqual(parsed.spans, [
+      { start: 0, end: 1.2 },
+      { start: 1.8, end: 2.1 },
+    ]);
+  } finally {
+    rmSync(dir, { recursive: true, force: true });
+  }
+});
+
+function word(id, text, start, end) {
+  return { id, text, start, end };
+}

skills/media-use/scripts/lib/parakeet-words.mjs

@@ -0,0 +1,27 @@
+// Merge Parakeet-MLX token timestamps into word timestamps.
+//
+// parakeet-mlx JSON emits SUB-WORD tokens (" H", "ello", ...) with per-token
+// start/end. Captions + transcript-cut need WORD timestamps, so join tokens
+// into words on the space boundary: a token whose text starts with a space
+// (or the very first token) begins a new word; the rest append. Output matches
+// the { words: [{ text, start, end }] } shape the rest of media-use consumes
+// (see words.mjs / cutlist.mjs).
+
+export function mergeTokensToWords(parakeet) {
+  const sentences = Array.isArray(parakeet?.sentences) ? parakeet.sentences : [];
+  const words = [];
+  for (const s of sentences) {
+    for (const t of s.tokens ?? []) {
+      const raw = typeof t.text === "string" ? t.text : "";
+      const startsWord = raw.startsWith(" ") || words.length === 0;
+      if (startsWord) {
+        words.push({ text: raw.trim(), start: t.start, end: t.end });
+      } else {
+        const w = words[words.length - 1];
+        w.text += raw;
+        w.end = t.end;
+      }
+    }
+  }
+  return { text: (parakeet?.text ?? "").trim(), words: words.filter((w) => w.text.length > 0) };
+}

skills/media-use/scripts/lib/parakeet-words.test.mjs

@@ -0,0 +1,44 @@
+import { strict as assert } from "node:assert";
+import { test } from "node:test";
+import { mergeTokensToWords } from "./parakeet-words.mjs";
+
+test("mergeTokensToWords joins sub-word tokens on the space boundary", () => {
+  const parakeet = {
+    text: "Hello everyone. Um,",
+    sentences: [
+      {
+        tokens: [
+          { text: " H", start: 0.0, end: 0.24 },
+          { text: "ello", start: 0.24, end: 0.48 },
+          { text: " everyone.", start: 0.48, end: 1.28 },
+          { text: " Um,", start: 1.28, end: 1.92 },
+        ],
+      },
+    ],
+  };
+  const { words } = mergeTokensToWords(parakeet);
+  assert.deepEqual(words, [
+    { text: "Hello", start: 0.0, end: 0.48 },
+    { text: "everyone.", start: 0.48, end: 1.28 },
+    { text: "Um,", start: 1.28, end: 1.92 },
+  ]);
+});
+
+test("mergeTokensToWords spans multiple sentences and drops empties", () => {
+  const parakeet = {
+    text: "Hi there",
+    sentences: [
+      { tokens: [{ text: "Hi", start: 0, end: 0.2 }] },
+      { tokens: [{ text: " there", start: 0.5, end: 0.9 }] },
+    ],
+  };
+  const { words } = mergeTokensToWords(parakeet);
+  assert.equal(words.length, 2);
+  assert.equal(words[1].text, "there");
+  assert.equal(words[1].start, 0.5);
+});
+
+test("mergeTokensToWords tolerates missing sentences/tokens", () => {
+  assert.deepEqual(mergeTokensToWords({}).words, []);
+  assert.deepEqual(mergeTokensToWords({ sentences: [{}] }).words, []);
+});

skills/media-use/scripts/transcribe.mjs

@@ -0,0 +1,172 @@
+#!/usr/bin/env node
+
+import { execFileSync } from "node:child_process";
+import {
+  existsSync,
+  readFileSync,
+  writeFileSync,
+  copyFileSync,
+  renameSync,
+  mkdtempSync,
+  rmSync,
+} from "node:fs";
+import { homedir, tmpdir } from "node:os";
+import { basename, extname, join, resolve } from "node:path";
+import { parseArgs } from "node:util";
+import { mergeTokensToWords } from "./lib/parakeet-words.mjs";
+import { track } from "./lib/telemetry.mjs";
+
+// The DEFAULT local transcription path. Prefers NVIDIA Parakeet-TDT via
+// parakeet-mlx, which beats whisper.cpp on the Open ASR Leaderboard (~6.05% vs
+// 7.44% avg WER, and 4.73% vs 5.96% on noisy test-other) and is 5-10x faster
+// with native punctuation. Emits { text, words:[{text,start,end}] } (word
+// timestamps merged from Parakeet's sub-word tokens) for transcript-cut /
+// captions / the audio engine.
+//
+// Parakeet v3 covers English + 25 European languages. For other languages, or
+// when parakeet-mlx is not installed, it falls back to the packaged whisper.cpp
+// (`hyperframes transcribe`, 99 languages). `--engine` forces one.
+
+const { values: args } = parseArgs({
+  options: {
+    input: { type: "string", short: "i" },
+    out: { type: "string", short: "o" },
+    engine: { type: "string", default: "auto" }, // auto | parakeet | whisper
+    model: { type: "string", default: "mlx-community/parakeet-tdt-0.6b-v3" },
+    json: { type: "boolean", default: false },
+    help: { type: "boolean", short: "h", default: false },
+  },
+  strict: true,
+});
+
+if (args.help) {
+  console.log(`media-use transcribe: better-than-whisper local ASR (Parakeet), whisper.cpp fallback
+
+Usage:
+  node transcribe.mjs --input audio.wav [--out audio.transcribe.json] [--engine auto|parakeet|whisper]
+
+Parakeet (default) beats whisper.cpp on accuracy + speed for English/European
+languages; whisper.cpp (99 languages) is the fallback. Install Parakeet once:
+  uv venv ~/.venvs/parakeet && VIRTUAL_ENV=~/.venvs/parakeet uv pip install parakeet-mlx`);
+  process.exit(0);
+}
+
+if (!args.input) {
+  console.error("error: --input is required");
+  process.exit(2);
+}
+const inputPath = resolve(args.input);
+if (!existsSync(inputPath)) {
+  console.error(`error: input not found: ${inputPath}`);
+  process.exit(2);
+}
+const outPath = resolve(
+  args.out || `${inputPath.slice(0, -extname(inputPath).length)}.transcribe.json`,
+);
+
+// Locate the parakeet-mlx runner the same way the CLI does: env override, then
+// the documented ~/.venvs/parakeet install, then PATH. Checking the venv (not
+// just PATH) is what keeps a user who followed the install docs verbatim from
+// silently falling through to whisper. Returns the runner path, or null.
+function resolveParakeet() {
+  for (const p of [
+    process.env.HYPERFRAMES_PARAKEET,
+    join(homedir(), ".venvs", "parakeet", "bin", "parakeet-mlx"),
+  ]) {
+    if (p && existsSync(p)) return p;
+  }
+  try {
+    execFileSync("parakeet-mlx", ["--help"], {
+      stdio: ["ignore", "ignore", "ignore"],
+      timeout: 20000,
+    });
+    return "parakeet-mlx";
+  } catch {
+    return null;
+  }
+}
+
+// Write via a sibling temp + atomic rename so a SIGKILL mid-write can't leave a
+// truncated transcript at outPath (downstream reads it as valid JSON).
+function atomicWrite(target, data) {
+  const tmp = `${target}.tmp-${process.pid}`;
+  writeFileSync(tmp, data);
+  renameSync(tmp, target);
+}
+
+function report(engine, wordCount) {
+  if (args.json) console.log(JSON.stringify({ ok: true, out: outPath, engine, words: wordCount }));
+  else
+    console.log(
+      `transcribed ${basename(inputPath)} -> ${outPath}${wordCount != null ? ` (${wordCount} words,` : " ("}${engine})`,
+    );
+}
+
+function runParakeet(runner) {
+  const workDir = mkdtempSync(join(tmpdir(), "media-use-asr-"));
+  try {
+    execFileSync(
+      runner,
+      [inputPath, "--model", args.model, "--output-format", "json", "--output-dir", workDir],
+      { stdio: ["ignore", "pipe", "pipe"], timeout: 1_800_000 },
+    );
+    const jsonPath = join(workDir, `${basename(inputPath, extname(inputPath))}.json`);
+    if (!existsSync(jsonPath)) throw new Error("parakeet produced no JSON");
+    const merged = mergeTokensToWords(JSON.parse(readFileSync(jsonPath, "utf8")));
+    atomicWrite(outPath, JSON.stringify(merged, null, 2));
+    report("parakeet", merged.words.length);
+  } finally {
+    rmSync(workDir, { recursive: true, force: true });
+  }
+}
+
+// whisper.cpp via the packaged CLI: writes transcript.json into --dir; relocate to --out.
+function runWhisper() {
+  const workDir = mkdtempSync(join(tmpdir(), "media-use-whisper-"));
+  try {
+    execFileSync("npx", ["hyperframes", "transcribe", inputPath, "--dir", workDir], {
+      stdio: ["ignore", "pipe", "pipe"],
+      timeout: 1_800_000,
+    });
+    const produced = join(workDir, "transcript.json");
+    if (!existsSync(produced)) throw new Error("whisper produced no transcript.json");
+    const tmp = `${outPath}.tmp-${process.pid}`;
+    copyFileSync(produced, tmp);
+    renameSync(tmp, outPath); // atomic publish
+    let words;
+    try {
+      const t = JSON.parse(readFileSync(outPath, "utf8"));
+      words = Array.isArray(t?.words) ? t.words.length : undefined;
+    } catch {
+      /* leave undefined */
+    }
+    report("whisper", words);
+  } finally {
+    rmSync(workDir, { recursive: true, force: true });
+  }
+}
+
+try {
+  const parakeetBin = resolveParakeet();
+  const engine =
+    args.engine === "parakeet" || args.engine === "whisper"
+      ? args.engine
+      : parakeetBin
+        ? "parakeet"
+        : "whisper";
+  if (engine === "parakeet") {
+    if (!parakeetBin) {
+      throw new Error(
+        "parakeet-mlx not found (checked $HYPERFRAMES_PARAKEET, ~/.venvs/parakeet, and PATH). Install: uv venv ~/.venvs/parakeet && VIRTUAL_ENV=~/.venvs/parakeet uv pip install parakeet-mlx (or use --engine whisper)",
+      );
+    }
+    runParakeet(parakeetBin);
+  } else {
+    runWhisper();
+  }
+  await track("media_use_transcribe", { engine });
+} catch (err) {
+  if (args.json) console.log(JSON.stringify({ ok: false, error: err.message }));
+  else console.error(`error: transcription failed: ${err.message}`);
+  process.exit(1);
+}

skills/media-use/scripts/transcript-cut.mjs

@@ -0,0 +1,238 @@
+#!/usr/bin/env node
+
+import { execFileSync } from "node:child_process";
+import { mkdtempSync, mkdirSync, readFileSync, renameSync, rmSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { dirname, extname, join, resolve } from "node:path";
+import { parseArgs } from "node:util";
+import { compileCutList } from "./lib/cutlist.mjs";
+import { track } from "./lib/telemetry.mjs";
+
+const { values: args } = parseArgs({
+  options: {
+    input: { type: "string" },
+    transcript: { type: "string" },
+    remove: { type: "string" },
+    "remove-words": { type: "string" },
+    "remove-fillers": { type: "string" },
+    "cut-silence": { type: "string" },
+    keep: { type: "string" },
+    copy: { type: "boolean", default: false },
+    plan: { type: "boolean", default: false },
+    out: { type: "string" },
+    json: { type: "boolean", default: false },
+    help: { type: "boolean", short: "h", default: false },
+  },
+  strict: true,
+});
+
+if (args.help) {
+  console.log(`media-use transcript-cut — compile transcript edits into video cuts
+
+Usage:
+  node transcript-cut.mjs --input in.mp4 --transcript transcript.json --remove "12-15" --out out.mp4
+
+Options:
+  --input             Source video/audio file
+  --transcript        JSON word transcript, array or { words: [...] }
+  --remove            Time ranges to remove, seconds: a-b,c-d
+  --remove-words      Word-index ranges to remove: 12-18,40-41
+  --remove-fillers    Comma list of filler words to remove
+  --cut-silence       Remove inter-word gaps longer than this many seconds
+  --keep              Inverse mode: direct kept ranges, mutually exclusive with removal
+  --copy              Use stream copy for faster, keyframe-snapped cuts
+  --plan              Print kept segment JSON and exit without ffmpeg
+  --out               Output file
+  --json              Output JSON status
+  --help, -h          Show this help`);
+  process.exit(0);
+}
+
+try {
+  run();
+  await track("media_use_transcript_cut", {
+    mode: args.plan ? "plan" : "encode",
+    remove_fillers: !!args["remove-fillers"],
+    cut_silence: !!args["cut-silence"],
+    ranges: !!args.remove,
+    keep: !!args.keep,
+  });
+} catch (err) {
+  if (args.json) console.log(JSON.stringify({ ok: false, error: err.message }));
+  else console.error(`error: ${err.message}`);
+  process.exit(1);
+}
+
+function run() {
+  if (!args.transcript) throw new Error("--transcript is required");
+  const transcript = JSON.parse(readFileSync(resolve(args.transcript), "utf8"));
+  const segments = compileCutList(transcript, {
+    remove: args.remove,
+    removeWords: args["remove-words"],
+    removeFillers: args["remove-fillers"],
+    cutSilence: args["cut-silence"],
+    keep: args.keep,
+  });
+
+  if (args.plan) {
+    console.log(JSON.stringify(segments));
+    return;
+  }
+
+  if (!args.input || !args.out)
+    throw new Error("--input and --out are required unless --plan is set");
+  if (segments.length === 0) throw new Error("cut list has no kept segments");
+
+  const inputPath = resolve(args.input);
+  const outPath = resolve(args.out);
+  mkdirSync(dirname(outPath), { recursive: true });
+  const tmpDir = mkdtempSync(join(tmpdir(), "media-use-cut-"));
+  const keptSeconds = sumDurations(segments);
+  const totalSeconds = probeDuration(inputPath);
+
+  try {
+    const parts = segments.map((segment, index) => {
+      const out = join(
+        tmpDir,
+        `segment-${String(index).padStart(4, "0")}${extname(outPath) || ".mp4"}`,
+      );
+      cutSegment(inputPath, segment, out, Boolean(args.copy));
+      return out;
+    });
+    const listPath = join(tmpDir, "list.txt");
+    writeFileSync(
+      listPath,
+      parts.map((part) => `file '${escapeConcatPath(part)}'`).join("\n") + "\n",
+    );
+    // Encode to a sibling temp (same extension so ffmpeg picks the right muxer),
+    // then atomic-rename so a SIGKILL mid-encode can't leave a truncated outPath.
+    const tmpOut = `${outPath}.part${extname(outPath) || ".mp4"}`;
+    execFileSync(
+      "ffmpeg",
+      ["-y", "-f", "concat", "-safe", "0", "-i", listPath, "-c", "copy", tmpOut],
+      {
+        stdio: "ignore",
+      },
+    );
+    renameSync(tmpOut, outPath);
+  } finally {
+    rmSync(tmpDir, { recursive: true, force: true });
+  }
+
+  // Stream copy can only cut on keyframes; on sparse-keyframe footage the snap
+  // can silently swallow the whole cut. Compare, then surface the drift in BOTH
+  // the stderr warning (human) and the --json result (pipelines).
+  let copyDrift = null;
+  if (args.copy) {
+    const outSeconds = probeDuration(outPath);
+    if (Math.abs(outSeconds - keptSeconds) > 1) {
+      copyDrift = { produced_s: round3(outSeconds), expected_s: round3(keptSeconds) };
+      if (!args.json) {
+        console.error(
+          `warning: --copy keyframe snapping produced ${round3(outSeconds)}s instead of ${round3(keptSeconds)}s kept; drop --copy for frame-accurate cuts`,
+        );
+      }
+    }
+  }
+
+  if (args.json) {
+    console.log(
+      JSON.stringify({
+        ok: true,
+        input: inputPath,
+        out: outPath,
+        segments,
+        kept_s: round3(keptSeconds),
+        total_s: round3(totalSeconds),
+        ...(copyDrift && { copy_drift: copyDrift }),
+      }),
+    );
+    return;
+  }
+
+  console.log(
+    `cut ${inputPath} -> ${outPath} (${segments.length} segments, ${fmt(keptSeconds)}s kept of ${fmt(
+      totalSeconds,
+    )}s)`,
+  );
+  console.log(`next: resolve --from ${outPath} --type <type>`);
+}
+
+function cutSegment(inputPath, segment, outPath, copy) {
+  const argv = [
+    "-y",
+    "-nostdin",
+    "-ss",
+    fmt(segment.start),
+    "-i",
+    inputPath,
+    "-to",
+    fmt(segment.end - segment.start),
+  ];
+  if (copy) {
+    argv.push("-c", "copy", "-avoid_negative_ts", "make_zero");
+  } else {
+    argv.push(...encodeArgsFor(extname(outPath).toLowerCase()));
+  }
+  argv.push(outPath);
+  execFileSync("ffmpeg", argv, { stdio: "ignore" });
+}
+
+// Codec set per output container. Audio-only outputs must not get the
+// video-centric aac/x264 set (aac inside .wav breaks timing entirely).
+function encodeArgsFor(ext) {
+  if (ext === ".wav") return ["-c:a", "pcm_s16le"];
+  if (ext === ".mp3") return ["-c:a", "libmp3lame", "-q:a", "2"];
+  if (ext === ".m4a" || ext === ".aac") return ["-c:a", "aac"];
+  if (ext === ".flac") return ["-c:a", "flac"];
+  return [
+    "-c:v",
+    "libx264",
+    "-preset",
+    "veryfast",
+    "-crf",
+    "18",
+    "-c:a",
+    "aac",
+    "-movflags",
+    "+faststart",
+  ];
+}
+
+function probeDuration(filePath) {
+  const raw = execFileSync(
+    "ffprobe",
+    [
+      "-v",
+      "error",
+      "-show_entries",
+      "format=duration",
+      "-of",
+      "default=noprint_wrappers=1:nokey=1",
+      filePath,
+    ],
+    { encoding: "utf8" },
+  );
+  const duration = Number(raw.trim());
+  if (!Number.isFinite(duration) || duration <= 0)
+    throw new Error(`could not probe duration: ${filePath}`);
+  return duration;
+}
+
+function escapeConcatPath(filePath) {
+  return filePath.replace(/'/g, "'\\''");
+}
+
+function sumDurations(segments) {
+  return segments.reduce((sum, segment) => sum + (segment.end - segment.start), 0);
+}
+
+function fmt(n) {
+  return round3(n)
+    .toFixed(3)
+    .replace(/\.?0+$/, "");
+}
+
+function round3(n) {
+  return Math.round(Number(n) * 1000) / 1000;
+}