dsh-hyperframes 0.2.0 → 0.3.0

package/skills/media-use/audio/scripts/lib/python.test.mjs

@@ -0,0 +1,68 @@
+import { test } from "node:test";
+import assert from "node:assert/strict";
+import { resolvePythonCommand, pythonInvocation } from "./python.mjs";
+
+// Regression: on Windows a standard python.org install has no `python3.exe`
+// (only `python.exe` + the `py` launcher), so `spawn("python3", …)` ENOENTs and
+// every Python-backed audio feature silently no-ops. resolvePythonCommand takes
+// injectable platform/probe params so all branches are testable without
+// spawning a real interpreter.
+
+// probeFor(names): a probe that reports success only for the given argv-0 names.
+function probeFor(...names) {
+  const ok = new Set(names);
+  return (cmd) => ok.has(cmd);
+}
+
+test("non-win32 uses python3 when it runs", () => {
+  assert.deepEqual(resolvePythonCommand("linux", probeFor("python3")), ["python3"]);
+  assert.deepEqual(resolvePythonCommand("darwin", probeFor("python3")), ["python3"]);
+});
+
+test("win32 prefers python3 when the Microsoft Store build provides it", () => {
+  assert.deepEqual(resolvePythonCommand("win32", probeFor("python3", "python", "py")), ["python3"]);
+});
+
+test("win32 falls back to python.exe when python3 is absent (python.org install)", () => {
+  // The exact reported scenario: no python3, but `python` exists.
+  assert.deepEqual(resolvePythonCommand("win32", probeFor("python", "py")), ["python"]);
+});
+
+test("win32 falls back to the py launcher with -3 when only py exists", () => {
+  assert.deepEqual(resolvePythonCommand("win32", probeFor("py")), ["py", "-3"]);
+});
+
+test("py launcher is probed as `py -3 --version`, not bare `py`", () => {
+  const seen = [];
+  const probe = (cmd, args) => {
+    seen.push([cmd, ...args]);
+    return cmd === "py";
+  };
+  resolvePythonCommand("win32", probe);
+  assert.deepEqual(seen.at(-1), ["py", "-3", "--version"]);
+});
+
+test("falls back to the canonical name (loud failure, unchanged) when nothing runs", () => {
+  // No interpreter anywhere — must not throw, and must return python3 so the
+  // eventual spawn fails exactly as it did before this fix, never worse.
+  assert.deepEqual(
+    resolvePythonCommand("win32", () => false),
+    ["python3"],
+  );
+  assert.deepEqual(
+    resolvePythonCommand("linux", () => false),
+    ["python3"],
+  );
+});
+
+test("pythonInvocation prepends the resolved prefix ahead of caller args", () => {
+  assert.deepEqual(pythonInvocation(["-c", "import x"], ["python"]), {
+    cmd: "python",
+    args: ["-c", "import x"],
+  });
+  // The py launcher's -3 must stay ahead of the caller's own arguments.
+  assert.deepEqual(pythonInvocation(["-c", "import x"], ["py", "-3"]), {
+    cmd: "py",
+    args: ["-3", "-c", "import x"],
+  });
+});

package/skills/media-use/audio/scripts/lib/sfx.mjs

@@ -0,0 +1,143 @@
+// 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}:${c.name}`;
+    if (seen.has(k)) return false;
+    seen.add(k);
+    return true;
+  });
+
+  if (heygenOK) {
+    for (const { id, name } of uniq) {
+      try {
+        // SFX hits score low (~0.5–0.67), below the API's default 0.7 which
+        // silently drops most named cues — floor to 0.4. (BGM/music score high
+        // and keep the default.)
+        const results = await searchSounds(name, "sound_effects", headers, {
+          limit: 3,
+          minScore: 0.4,
+        });
+        if (!results.length) {
+          anomalies.push(`sfx "${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);
+    // The bundled library may be incomplete: some installs of the skill ship
+    // manifest.json without the actual mp3s. Pushing an sfx entry that points at
+    // a file we never copied produces a dangling reference that silently drops
+    // downstream ("not on disk"). Surface it as a loud anomaly and skip the cue
+    // instead, so the audio_meta never references a missing file.
+    if (!existsSync(dest)) {
+      if (!existsSync(src)) {
+        anomalies.push(
+          `sfx "${name}" (id ${id}): bundled file ${hit.file} missing from the offline ` +
+            `library (${sfxLibDir}) — skipped. Reinstall the media-use skill to ` +
+            `restore assets/sfx/*.mp3, or configure a HeyGen credential for retrieval.`,
+        );
+        continue;
+      }
+      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 };
+}

package/skills/media-use/audio/scripts/lib/sfx.test.mjs

@@ -0,0 +1,69 @@
+import { test } from "node:test";
+import assert from "node:assert/strict";
+import { mkdtempSync, mkdirSync, writeFileSync, existsSync, rmSync } from "node:fs";
+import { join } from "node:path";
+import { tmpdir } from "node:os";
+import { resolveSfx } from "./sfx.mjs";
+
+// Offline (no HeyGen) SFX resolution: the bundled library may ship manifest.json
+// without the actual mp3s. The old code copied only when the source existed but
+// pushed the sfx entry unconditionally — producing a dangling reference that
+// silently dropped downstream ("not on disk"). These tests lock in the loud
+// behavior: a present file is copied + referenced; a missing file yields an
+// anomaly and NO dangling entry.
+
+async function withDirs(fn) {
+  const root = mkdtempSync(join(tmpdir(), "hf-sfx-"));
+  const libDir = join(root, "lib");
+  const projDir = join(root, "proj");
+  mkdirSync(libDir, { recursive: true });
+  mkdirSync(projDir, { recursive: true });
+  try {
+    // `await` is load-bearing: without it the finally cleanup runs before the
+    // async test body resolves, deleting the temp dir mid-assertion.
+    return await fn({ libDir, projDir });
+  } finally {
+    rmSync(root, { recursive: true, force: true });
+  }
+}
+
+test("offline: copies and references a present bundled file", async () => {
+  await withDirs(async ({ libDir, projDir }) => {
+    writeFileSync(
+      join(libDir, "manifest.json"),
+      JSON.stringify({ whoosh: { file: "whoosh.mp3", duration: 0.8 } }),
+    );
+    writeFileSync(join(libDir, "whoosh.mp3"), "ID3-fake-bytes");
+    const { sfx, anomalies } = await resolveSfx({
+      cues: [{ id: "s1", name: "whoosh" }],
+      heygenOK: false,
+      hyperframesDir: projDir,
+      sfxLibDir: libDir,
+    });
+    assert.equal(sfx.length, 1);
+    assert.equal(sfx[0].file, "assets/sfx/whoosh.mp3");
+    assert.equal(sfx[0].source, "local");
+    assert.ok(existsSync(join(projDir, "assets/sfx/whoosh.mp3")), "mp3 copied into project");
+    assert.equal(anomalies.length, 0);
+  });
+});
+
+test("offline: a matched-but-missing bundled file yields an anomaly and NO dangling entry", async () => {
+  await withDirs(async ({ libDir, projDir }) => {
+    // Manifest names whoosh.mp3, but the mp3 was never shipped (the reported bug).
+    writeFileSync(
+      join(libDir, "manifest.json"),
+      JSON.stringify({ whoosh: { file: "whoosh.mp3", duration: 0.8 } }),
+    );
+    const { sfx, anomalies } = await resolveSfx({
+      cues: [{ id: "s1", name: "whoosh" }],
+      heygenOK: false,
+      hyperframesDir: projDir,
+      sfxLibDir: libDir,
+    });
+    assert.equal(sfx.length, 0, "no dangling entry for a file that was never copied");
+    assert.equal(anomalies.length, 1);
+    assert.match(anomalies[0], /missing from the offline library/);
+    assert.ok(!existsSync(join(projDir, "assets/sfx/whoosh.mp3")), "nothing copied");
+  });
+});

package/skills/media-use/audio/scripts/lib/tts.mjs

@@ -0,0 +1,378 @@
+// tts.mjs — multi-provider TTS for the media audio engine. The provider chain,
+// auto-detected from env, is the one documented in ../SKILL.md:
+//
+//   1. HeyGen (Starfish)  — $HEYGEN_API_KEY / $HYPERFRAMES_API_KEY / ~/.heygen.
+//        Direct v3 REST (NOT `hyperframes tts`, which in the published build is
+//        Kokoro-only and silently ignores a HeyGen key). Returns word_timestamps
+//        in the same call, so no separate transcribe pass.
+//   2. ElevenLabs         — $ELEVENLABS_API_KEY + `pip install elevenlabs`. No
+//        word timings → caller chains transcribeWav().
+//   3. Kokoro-82M (local) — always available, via the published `hyperframes tts`
+//        CLI. No word timings → caller chains transcribeWav().
+//
+// "HeyGen available" is decided by CREDENTIAL presence (heygenCredential), never
+// by the CLI — see the note above.
+
+import { spawn, spawnSync } from "node:child_process";
+import { existsSync, mkdirSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { dirname, join } from "node:path";
+import { heygenAuthHeaders, heygenCredential, heygenJSON } from "./heygen.mjs";
+import { pythonInvocation } from "./python.mjs";
+
+// ── provider detection ────────────────────────────────────────────────────────
+export function heygenAvailable() {
+  return heygenCredential() !== null;
+}
+export function elevenlabsAvailable() {
+  if (!process.env.ELEVENLABS_API_KEY) return false;
+  const { cmd, args } = pythonInvocation(["-c", "import elevenlabs"]);
+  const r = spawnSync(cmd, args, {
+    stdio: "ignore",
+  });
+  return r.status === 0;
+}
+
+// First available provider wins; an explicit choice is honored (and validated).
+export function pickProvider(userProvider) {
+  if (userProvider) {
+    if (!["heygen", "elevenlabs", "kokoro"].includes(userProvider))
+      throw new Error(`invalid provider "${userProvider}" (heygen | elevenlabs | kokoro)`);
+    if (userProvider === "heygen" && !heygenAvailable())
+      throw new Error(
+        "provider=heygen but no HeyGen credentials (set $HEYGEN_API_KEY or run `npx hyperframes auth login`)",
+      );
+    if (userProvider === "elevenlabs" && !process.env.ELEVENLABS_API_KEY)
+      throw new Error("provider=elevenlabs but $ELEVENLABS_API_KEY is not set");
+    return userProvider;
+  }
+  return heygenAvailable() ? "heygen" : elevenlabsAvailable() ? "elevenlabs" : "kokoro";
+}
+
+// ── voice resolution ──────────────────────────────────────────────────────────
+// HeyGen /v3/voices/speech only accepts STARFISH voice_ids; auto-pick the first
+// English public starfish voice when none is pinned. ElevenLabs/Kokoro have
+// their own defaults.
+export async function resolveVoiceId({ provider, userVoice, lang = "en" }) {
+  if (userVoice) return userVoice;
+  if (provider === "elevenlabs") return "21m00Tcm4TlvDq8ikWAM"; // Rachel
+  if (provider === "kokoro") {
+    if (lang === "en") return "am_michael";
+    throw new Error("Kokoro non-English needs an explicit --voice (see references/tts.md)");
+  }
+  // heygen — pin a fixed English default so the choice is deterministic. The old
+  // "first English voice the API returns" drifts whenever HeyGen re-sorts the
+  // public catalog. Marcia (mature, low female). Override with --voice / request.voice.
+  if (lang === "en") return "05f19352e8f74b0392a8f411eba40de1"; // Marcia · English · female
+  // Non-English: no fixed default — fall back to the first matching catalog voice.
+  const payload = await heygenJSON(`/voices?engine=starfish&type=public&limit=50`, {
+    headers: heygenAuthHeaders(),
+  });
+  const voices = payload.data ?? payload.voices ?? [];
+  const pick = voices.find((v) => v.language === "English") ?? voices[0];
+  if (!pick) throw new Error("no public starfish voice to default to — pass --voice");
+  return pick.voice_id;
+}
+
+// ── helpers ─────────────────────────────────────────────────────────────────
+export function withWordIds(words) {
+  return (words ?? []).map((w, i) => ({
+    id: `w${i}`,
+    text: w.text,
+    start: w.start,
+    end: w.end,
+  }));
+}
+
+// `ffmpeg -i <file>` prints a `Duration: HH:MM:SS.ms` line to stderr even
+// though it exits non-zero with no output requested. Parsing pulled out as
+// a pure function so the ENOENT fallback below can be tested without
+// depending on whether ffprobe/ffmpeg are actually installed on the
+// machine running the tests.
+export function parseFfmpegDurationBanner(stderrText) {
+  const match = /Duration:\s*(\d+):(\d+):(\d+(?:\.\d+)?)/.exec(stderrText ?? "");
+  if (!match) return NaN;
+  const [, hours, minutes, seconds] = match;
+  return Number(hours) * 3600 + Number(minutes) * 60 + Number(seconds);
+}
+
+// Some "essentials"-style ffmpeg distributions (common on Windows) ship
+// ffmpeg.exe without ffprobe.exe. ffprobeDuration's caller (audio.mjs)
+// otherwise reads a spurious NaN as "the WAV file is corrupt" and drops an
+// already-successfully-synthesized TTS line, rather than "the tool for
+// measuring it is missing".
+function ffmpegDurationFallback(absPath) {
+  const r = spawnSync("ffmpeg", ["-i", absPath], { encoding: "utf8" });
+  return parseFfmpegDurationBanner(r.stderr);
+}
+
+export function ffprobeDuration(absPath) {
+  const r = spawnSync(
+    "ffprobe",
+    ["-v", "error", "-show_entries", "format=duration", "-of", "default=nw=1:nk=1", "--", absPath],
+    { encoding: "utf8" },
+  );
+  if (r.error?.code === "ENOENT") return ffmpegDurationFallback(absPath);
+  if (r.status !== 0) return NaN;
+  return parseFloat(String(r.stdout).trim());
+}
+
+export function resolveNpxCliFromNpmExecPath(
+  npmExecPath = process.env.npm_execpath,
+  pathExists = existsSync,
+) {
+  if (!npmExecPath) return null;
+  const fileName = npmExecPath.replace(/\\/g, "/").split("/").pop()?.toLowerCase();
+  const npxCliPath =
+    fileName === "npx-cli.js" ? npmExecPath : join(dirname(npmExecPath), "npx-cli.js");
+  return pathExists(npxCliPath) ? npxCliPath : null;
+}
+
+export function resolveNpxCliPath(
+  npmExecPath = process.env.npm_execpath,
+  nodeExecPath = process.env.npm_node_execpath || process.execPath,
+  pathExists = existsSync,
+) {
+  const fromNpm = resolveNpxCliFromNpmExecPath(npmExecPath, pathExists);
+  if (fromNpm) return fromNpm;
+  const besideNode = join(dirname(nodeExecPath), "node_modules", "npm", "bin", "npx-cli.js");
+  return pathExists(besideNode) ? besideNode : null;
+}
+
+export function resolveSpawnCommand(
+  cmd,
+  args,
+  opts = {},
+  platform = process.platform,
+  env = process.env,
+  pathExists = existsSync,
+) {
+  if (cmd !== "npx" || platform !== "win32") {
+    return { cmd, args, opts: { stdio: "ignore", ...opts } };
+  }
+
+  // On Windows, npx resolves to npx.cmd, which Node cannot execute directly.
+  // Avoid `shell:true` and the .cmd shim entirely by invoking npm's JS CLI with
+  // node, preserving request-provided values as argv data instead of shell text.
+  const nodeExecPath = env.npm_node_execpath || process.execPath;
+  const npxCliPath = resolveNpxCliPath(env.npm_execpath, nodeExecPath, pathExists);
+  if (!npxCliPath) return null;
+  return {
+    cmd: nodeExecPath,
+    args: [npxCliPath, ...args.map((arg) => String(arg))],
+    opts: { stdio: "ignore", windowsHide: true, ...opts },
+  };
+}
+
+// `platform`/`spawnFn` params (default process.platform / the real spawn)
+// exist so tests can exercise the win32 branch without mocking node:child_process
+// (its ESM exports are non-configurable, so mock.method can't patch it).
+// One-shot so a whole batch of TTS lines doesn't repeat the same diagnostic.
+let _warnedNpxResolution = false;
+/** Test-only: reset the one-shot npx-resolution warning latch. */
+export function _resetNpxResolutionWarnForTests() {
+  _warnedNpxResolution = false;
+}
+
+export function spawnP(
+  cmd,
+  args,
+  opts = {},
+  platform = process.platform,
+  spawnFn = spawn,
+  env = process.env,
+  pathExists = existsSync,
+) {
+  const resolved = resolveSpawnCommand(cmd, args, opts, platform, env, pathExists);
+  if (!resolved) {
+    // resolveSpawnCommand only returns null for the npx-on-win32 case where
+    // neither npm's configured CLI nor the beside-node fallback exists. Without
+    // this, every call silently returns status:-1 and stdio:"ignore" hides why.
+    if (!_warnedNpxResolution) {
+      _warnedNpxResolution = true;
+      const reason = env.npm_execpath
+        ? `npm_execpath (${env.npm_execpath}) and the beside-node npm fallback could not be found`
+        : "npm_execpath is unset and the beside-node npm fallback could not be found";
+      console.error(
+        `[media-use] Cannot run "${cmd}" on Windows: ${reason}. ` +
+          `Every "${cmd}" call is being skipped. Install npm with Node, or run via ` +
+          `\`npx\`/\`npm run\` with a valid npm_execpath.`,
+      );
+    }
+    return Promise.resolve({ status: -1 });
+  }
+  return new Promise((resolve) => {
+    const p = spawnFn(resolved.cmd, resolved.args, resolved.opts);
+    p.on("exit", (code) => resolve({ status: code ?? -1 }));
+    p.on("error", () => resolve({ status: -1 }));
+  });
+}
+
+// mp3/whatever bytes → wav 44.1k mono at destWav (ffmpeg detects true format).
+function transcodeToWav(bytes, destWav) {
+  const td = mkdtempSync(join(tmpdir(), "hf-tts-"));
+  const tmp = join(td, "a.mp3");
+  writeFileSync(tmp, bytes);
+  mkdirSync(dirname(destWav), { recursive: true });
+  const ff = spawnSync(
+    "ffmpeg",
+    ["-y", "-loglevel", "error", "-i", tmp, "-ar", "44100", "-ac", "1", destWav],
+    { stdio: "ignore" },
+  );
+  rmSync(td, { recursive: true, force: true });
+  return ff.status === 0 && existsSync(destWav);
+}
+
+const ELEVENLABS_PY = `
+import os, sys
+from elevenlabs.client import ElevenLabs
+from elevenlabs import save
+client = ElevenLabs(api_key=os.environ["ELEVENLABS_API_KEY"])
+text = open(sys.argv[1]).read()
+audio = client.text_to_speech.convert(
+    text=text, voice_id=sys.argv[2],
+    model_id="eleven_multilingual_v2", output_format="mp3_44100_128",
+)
+save(audio, sys.argv[3])
+`;
+
+// ── synthesize one line ───────────────────────────────────────────────────────
+// Writes wav at wavAbs. Returns { ok, words, error } — words is the raw
+// [{text,start,end}] array for HeyGen (native), or null for ElevenLabs/Kokoro
+// (caller must transcribeWav). Never throws; failures return { ok:false, error }
+// where `error` states WHY (so the caller can surface it, not a bare "TTS failed").
+export async function synthesizeOne({
+  provider,
+  text,
+  voiceId,
+  lang = "en",
+  speed = 1.0,
+  wavAbs,
+  hyperframesDir,
+}) {
+  if (provider === "heygen") return synthesizeHeygen({ text, voiceId, lang, speed, wavAbs });
+  if (provider === "elevenlabs") {
+    // The Python helper writes straight to wavAbs; unlike heygen (transcodeToWav)
+    // and kokoro (the `hyperframes tts` CLI), it does NOT create the parent dir,
+    // so on a fresh project (no assets/voice/ yet) the save fails and the line is
+    // silently dropped as "TTS failed - omitted". Create it first, like the other
+    // providers do. Guarded so a mkdir failure (EACCES/EROFS) returns
+    // { ok:false } like the rest of this branch rather than throwing (the
+    // function's contract is "never throws; failures return { ok:false }").
+    try {
+      mkdirSync(dirname(wavAbs), { recursive: true });
+    } catch {
+      return { ok: false, words: null };
+    }
+    const { cmd, args } = pythonInvocation([
+      "-c",
+      ELEVENLABS_PY,
+      writeTmpText(text),
+      voiceId,
+      wavAbs,
+    ]);
+    const r = await spawnP(cmd, args, {});
+    return synthResult(r, wavAbs, "elevenlabs (python)");
+  }
+  // kokoro — via the published CLI; --output is relative to the project dir.
+  const wavRel = relTo(hyperframesDir, wavAbs);
+  const args = ["hyperframes", "tts", writeTmpText(text), "--voice", voiceId, "--output", wavRel];
+  if (lang !== "en") args.push("--lang", lang);
+  const r = await spawnP("npx", args, { cwd: hyperframesDir });
+  return synthResult(r, wavAbs, "kokoro (npx hyperframes tts)");
+}
+
+// Shape a spawn result into { ok, words, error }, naming why on failure so the
+// caller surfaces it instead of a bare "TTS failed".
+export function synthResult(r, wavAbs, label) {
+  if (r.status === 0 && existsSync(wavAbs)) return { ok: true, words: null };
+  const why =
+    r.status !== 0 ? `${label} exited with status ${r.status}` : `${label} produced no wav file`;
+  return { ok: false, words: null, error: why };
+}
+
+// `deps` is injectable for tests; production uses the real network/ffmpeg impls.
+// Every failure path returns an `error` string so the caller can surface WHY a
+// line was dropped instead of the bare "TTS failed" that hid the real cause
+// (e.g. an HTTP 402 plan_upgrade_required thrown by heygenJSON was swallowed).
+export async function synthesizeHeygen({ text, voiceId, lang, speed, wavAbs }, deps = {}) {
+  const requestJSON = deps.heygenJSON ?? heygenJSON;
+  const authHeaders = deps.heygenAuthHeaders ?? heygenAuthHeaders;
+  const fetchImpl = deps.fetch ?? fetch;
+  const transcode = deps.transcodeToWav ?? transcodeToWav;
+  try {
+    const body = { text, voice_id: voiceId, speed };
+    if (lang !== "en") body.language = lang;
+    const payload = await requestJSON(`/voices/speech`, {
+      method: "POST",
+      headers: authHeaders(),
+      body,
+    });
+    const inner = payload.data ?? payload;
+    if (!inner.audio_url) {
+      return { ok: false, words: null, error: "HeyGen /voices/speech returned no audio_url" };
+    }
+    const res = await fetchImpl(inner.audio_url);
+    if (!res.ok) {
+      return { ok: false, words: null, error: `audio_url fetch failed: HTTP ${res.status}` };
+    }
+    const bytes = Buffer.from(await res.arrayBuffer());
+    // .wav output → transcode to 44.1k mono; .mp3 → raw bytes (no ffmpeg). The
+    // engine always asks for .wav; the standalone heygen-tts CLI may ask for .mp3.
+    if (wavAbs.endsWith(".wav")) {
+      if (!transcode(bytes, wavAbs)) {
+        return {
+          ok: false,
+          words: null,
+          error: "wav transcode failed (ffmpeg)",
+        };
+      }
+    } else {
+      mkdirSync(dirname(wavAbs), { recursive: true });
+      writeFileSync(wavAbs, bytes);
+    }
+    const words = Array.isArray(inner.word_timestamps)
+      ? inner.word_timestamps
+          .filter((w) => w && typeof w.word === "string" && isFinite(w.start) && isFinite(w.end))
+          .filter((w) => !/^<.*>$/.test(w.word.trim())) // drop <start>/<end> sentinels
+          .map((w) => ({ text: w.word, start: w.start, end: w.end }))
+      : [];
+    return { ok: true, words };
+  } catch (e) {
+    return { ok: false, words: null, error: e?.message ? String(e.message) : String(e) };
+  }
+}
+
+// ElevenLabs/Kokoro have no word timings — run Whisper over the wav. Returns the
+// flat [{id,text,start,end}] word array, or null. Each call uses a throwaway
+// --dir so parallel scenes don't collide on transcript.json.
+export async function transcribeWav({ wavRel, lang = "en", hyperframesDir }) {
+  const model = lang === "en" ? "small.en" : "small";
+  const td = mkdtempSync(join(tmpdir(), "hf-trans-"));
+  const args = ["hyperframes", "transcribe", wavRel, "--model", model, "--dir", td];
+  if (lang !== "en") args.push("--language", lang);
+  const r = await spawnP("npx", args, { cwd: hyperframesDir });
+  let words = null;
+  if (r.status === 0) {
+    const src = join(td, "transcript.json");
+    if (existsSync(src)) {
+      try {
+        const arr = JSON.parse(readFileSync(src, "utf8"));
+        if (Array.isArray(arr) && arr.length) words = arr;
+      } catch {}
+    }
+  }
+  rmSync(td, { recursive: true, force: true });
+  return words;
+}
+
+// ── tiny local utils ──────────────────────────────────────────────────────────
+function writeTmpText(text) {
+  const td = mkdtempSync(join(tmpdir(), "hf-txt-"));
+  const p = join(td, "line.txt");
+  writeFileSync(p, text);
+  return p;
+}
+function relTo(base, abs) {
+  return abs.startsWith(base + "/") ? abs.slice(base.length + 1) : abs;
+}