@ignix-social/editor 0.1.0

package/vendor/hyperframes/dist/skills/media-use/scripts/transcribe.mjs

@@ -0,0 +1,194 @@
+#!/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, stripVTControlCharacters } from "node:util";
+import { mergeTokensToWords } from "./lib/parakeet-words.mjs";
+import { track } from "./lib/telemetry.mjs";
+import { resolveNpxInvocation } from "./lib/npx-sync.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 whisper.cpp via
+// `hyperframes transcribe` (99 languages; the CLI resolves/builds whisper.cpp
+// on first use — it is not bundled). `--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:
+  npx hyperframes models install parakeet   (macOS, Windows, Linux with glibc 2.32+)
+  uv venv ~/.venvs/parakeet && VIRTUAL_ENV=~/.venvs/parakeet uv pip install parakeet-mlx   (Apple Silicon)`);
+  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, `${basename(inputPath, extname(inputPath))}.json`);
+    if (!existsSync(jsonPath)) throw new Error("parakeet produced no JSON");
+    const merged = mergeTokensToWords(JSON.parse(readFileSync(jsonPath, "utf8")));
+    atomicWrite(outPath, JSON.stringify(merged, null, 2));
+    report("parakeet", merged.words.length);
+  } finally {
+    rmSync(workDir, { recursive: true, force: true });
+  }
+}
+
+// The hyperframes CLI (its Parakeet, else whisper.cpp built on first use — see
+// SKILL.md): writes transcript.json into --dir; relocate to --out.
+function runCli(cliEngine) {
+  const workDir = mkdtempSync(join(tmpdir(), "media-use-whisper-"));
+  try {
+    // On Windows a bare "npx" is npx.cmd, which execFileSync cannot exec
+    // (spawnSync npx ENOENT) — resolveNpxInvocation reroutes it through
+    // node + npx-cli.js (and throws actionably when it can't), same
+    // mechanism as the audio engine's TTS spawns.
+    // Under auto or parakeet the CLI may run its own Parakeet; --json says which engine ran.
+    const resolved = resolveNpxInvocation(
+      ["hyperframes", "transcribe", inputPath, "--dir", workDir, "--engine", cliEngine, "--json"],
+      { stdio: ["ignore", "pipe", "pipe"], timeout: 1_800_000 },
+    );
+    let stdout;
+    try {
+      stdout = String(execFileSync(resolved.cmd, resolved.args, resolved.opts));
+    } catch (e) {
+      // stderr holds spinner redraws and --json prints the reason on stdout, so keep the last lines.
+      const tail = stripVTControlCharacters(`${e.stderr ?? ""}\n${e.stdout ?? ""}`)
+        .split(/[\r\n]+/)
+        .map((l) => l.trim())
+        .filter((l) => l && l !== "│")
+        .slice(-3)
+        .join("\n");
+      throw new Error(
+        `hyperframes transcribe failed (exit ${e.status ?? e.code})${tail ? `:\n${tail}` : ""}`,
+      );
+    }
+    const produced = join(workDir, "transcript.json");
+    if (!existsSync(produced))
+      throw new Error("hyperframes transcribe produced no transcript.json");
+    const tmp = `${outPath}.tmp-${process.pid}`;
+    copyFileSync(produced, tmp);
+    renameSync(tmp, outPath); // atomic publish
+    let words;
+    try {
+      const t = JSON.parse(readFileSync(outPath, "utf8"));
+      // The CLI writes a flat word array, not { words }.
+      words = Array.isArray(t) ? t.length : undefined;
+    } catch {
+      /* leave undefined */
+    }
+    let ran = "whisper";
+    try {
+      ran = JSON.parse(stdout.trim().split("\n").at(-1)).engine === "parakeet" ? "parakeet" : ran;
+    } catch {
+      /* no JSON line: keep whisper */
+    }
+    report(ran, words);
+    return ran;
+  } finally {
+    rmSync(workDir, { recursive: true, force: true });
+  }
+}
+
+try {
+  const parakeetBin = resolveParakeet();
+  const asked = args.engine === "parakeet" || args.engine === "whisper" ? args.engine : "auto";
+  // Without parakeet-mlx, the CLI's own Parakeet (any OS, `hyperframes models install parakeet`).
+  let engine = "parakeet";
+  if (asked !== "whisper" && parakeetBin) runParakeet(parakeetBin);
+  else engine = runCli(asked);
+  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);
+}

package/vendor/hyperframes/dist/skills/media-use/scripts/transcribe.test.mjs

@@ -0,0 +1,112 @@
+import assert from "node:assert/strict";
+import { execFileSync, spawnSync } from "node:child_process";
+import { chmodSync, mkdirSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import test from "node:test";
+import { fileURLToPath } from "node:url";
+
+// The stub stands in for `npx hyperframes transcribe <in> --dir <dir> ...`: it records its args,
+// writes the CLI's flat array and prints the CLI's --json line naming `cliEngine`.
+function runScript(engine, cliEngine) {
+  const root = mkdtempSync(join(tmpdir(), "media-use-transcribe-"));
+  try {
+    const bin = join(root, "bin");
+    mkdirSync(bin);
+    writeFileSync(
+      join(bin, "npx"),
+      `#!/bin/sh\necho "$@" > "${root}/args"\nwhile [ "$1" != "--dir" ]; do shift; done\n` +
+        `echo '[{"text":"a","start":0,"end":1},{"text":"b","start":1,"end":2}]' > "$2/transcript.json"\n` +
+        `echo '{"ok":true,"engine":"${cliEngine}"}'\n`,
+    );
+    chmodSync(join(bin, "npx"), 0o755);
+    const input = join(root, "in.wav");
+    writeFileSync(input, "");
+    const script = fileURLToPath(new URL("./transcribe.mjs", import.meta.url));
+    const env = { ...process.env, PATH: `${bin}:${process.env.PATH}`, HOME: root };
+    delete env.HYPERFRAMES_PARAKEET;
+    const out = execFileSync(
+      process.execPath,
+      [script, "--input", input, "--engine", engine, "--json"],
+      {
+        encoding: "utf8",
+        env: { ...env, HYPERFRAMES_MEDIA_HOME: join(root, "home"), HYPERFRAMES_NO_TELEMETRY: "1" },
+      },
+    );
+    return { result: JSON.parse(out.trim()), args: readFileSync(join(root, "args"), "utf8") };
+  } finally {
+    rmSync(root, { recursive: true, force: true });
+  }
+}
+
+test(
+  "--engine whisper makes the CLI run whisper and reports the flat transcript's word count",
+  { skip: process.platform === "win32" },
+  () => {
+    const { result, args } = runScript("whisper", "whisper");
+    assert.match(args, /--engine whisper --json/);
+    assert.equal(result.words, 2);
+    assert.equal(result.engine, "whisper");
+  },
+);
+
+test(
+  "auto reports the engine the CLI says it ran, Parakeet included",
+  { skip: process.platform === "win32" },
+  () => {
+    const { result, args } = runScript("auto", "parakeet");
+    assert.match(args, /--engine auto --json/);
+    assert.equal(result.engine, "parakeet");
+  },
+);
+
+test(
+  "--engine parakeet without parakeet-mlx asks the CLI for its Parakeet",
+  { skip: process.platform === "win32" },
+  () => {
+    const { result, args } = runScript("parakeet", "parakeet");
+    assert.match(args, /--engine parakeet --json/);
+    assert.equal(result.engine, "parakeet");
+  },
+);
+
+test(
+  "a failed --engine parakeet run reports the reason the CLI printed on stdout",
+  { skip: process.platform === "win32" },
+  () => {
+    const root = mkdtempSync(join(tmpdir(), "media-use-transcribe-"));
+    try {
+      const bin = join(root, "bin");
+      mkdirSync(bin);
+      const reason =
+        "Parakeet is not installed. Install it with: hyperframes models install parakeet";
+      writeFileSync(
+        join(bin, "npx"),
+        `#!/bin/sh\necho '{"ok":false,"error":"${reason}"}'\nexit 1\n`,
+      );
+      chmodSync(join(bin, "npx"), 0o755);
+      const input = join(root, "in.wav");
+      writeFileSync(input, "");
+      const script = fileURLToPath(new URL("./transcribe.mjs", import.meta.url));
+      const res = spawnSync(
+        process.execPath,
+        [script, "--input", input, "--engine", "parakeet", "--json"],
+        {
+          encoding: "utf8",
+          env: {
+            ...process.env,
+            HYPERFRAMES_PARAKEET: "",
+            PATH: `${bin}:${process.env.PATH}`,
+            HOME: root,
+            HYPERFRAMES_MEDIA_HOME: join(root, "home"),
+            HYPERFRAMES_NO_TELEMETRY: "1",
+          },
+        },
+      );
+      assert.equal(res.status, 1);
+      assert.match(JSON.parse(res.stdout.trim()).error, /hyperframes models install parakeet/);
+    } finally {
+      rmSync(root, { recursive: true, force: true });
+    }
+  },
+);

package/vendor/hyperframes/dist/skills/media-use/scripts/transcript-cut.mjs

@@ -0,0 +1,270 @@
+#!/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 { fadeFilterFor } from "./lib/transcriptCutFade.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: ${err.message}`);
+  process.exit(1);
+}
+
+function run() {
+  if (!args.transcript) throw new Error("--transcript is required");
+  const transcript = JSON.parse(readFileSync(resolve(args.transcript), "utf8"));
+  const segments = compileCutList(transcript, {
+    remove: args.remove,
+    removeWords: args["remove-words"],
+    removeFillers: args["remove-fillers"],
+    cutSilence: args["cut-silence"],
+    keep: args.keep,
+  });
+
+  if (args.plan) {
+    console.log(JSON.stringify(segments));
+    return;
+  }
+
+  if (!args.input || !args.out)
+    throw new Error("--input and --out are required unless --plan is set");
+  if (segments.length === 0) throw new Error("cut list has no kept segments");
+
+  const inputPath = resolve(args.input);
+  const outPath = resolve(args.out);
+  mkdirSync(dirname(outPath), { recursive: true });
+  const tmpDir = mkdtempSync(join(tmpdir(), "media-use-cut-"));
+  const keptSeconds = sumDurations(segments);
+  const totalSeconds = probeDuration(inputPath);
+
+  try {
+    const parts = segments.map((segment, index) => {
+      // Intermediates carry PCM audio, not the final codec. Encoding each
+      // segment to a lossy codec separately makes the encoder pad every segment
+      // with priming silence (~25-35ms for AAC), which concat then bakes in as a
+      // gap at each cut -- a defect distinct from, and surviving, the fades
+      // below. PCM has no priming, so audio is encoded exactly once, at concat.
+      const ext = args.copy ? extname(outPath) || ".mp4" : isAudioOnly(outPath) ? ".wav" : ".mkv";
+      const out = join(tmpDir, `segment-${String(index).padStart(4, "0")}${ext}`);
+      // --copy stays fade-free (stream copy cannot filter). A segment's true
+      // start/end (index 0's start, the last segment's end) borders nothing
+      // kept, so only an interior splice edge gets a ramp.
+      const fade = args.copy
+        ? null
+        : fadeFilterFor(segment.end - segment.start, {
+            fadeIn: index > 0,
+            fadeOut: index < segments.length - 1,
+          });
+      cutSegment(inputPath, segment, out, args.copy, fade);
+      return out;
+    });
+    const listPath = join(tmpDir, "list.txt");
+    writeFileSync(
+      listPath,
+      parts.map((part) => `file '${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"}`;
+    // --copy already produced final-codec segments, so concat can stream-copy.
+    // Otherwise the PCM intermediates are encoded here, once, for the whole file.
+    const concatCodecs = args.copy
+      ? ["-c", "copy"]
+      : isAudioOnly(outPath)
+        ? encodeArgsFor(extname(outPath).toLowerCase())
+        : ["-c:v", "copy", "-c:a", "aac", "-b:a", "192k", "-movflags", "+faststart"];
+    execFileSync(
+      "ffmpeg",
+      ["-y", "-f", "concat", "-safe", "0", "-i", listPath, ...concatCodecs, 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, fade) {
+  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 if (extname(outPath).toLowerCase() === ".mkv") {
+    // Concat splices raw segment edges together; without a short ramp the
+    // waveform steps discontinuously at every boundary and you hear a click.
+    if (fade) argv.push("-af", fade);
+    // Video intermediate: keep the picture cheap and the audio uncompressed.
+    argv.push("-c:v", "libx264", "-preset", "veryfast", "-crf", "18", "-c:a", "pcm_s16le");
+  } else {
+    if (fade) argv.push("-af", fade);
+    argv.push("-c:a", "pcm_s16le");
+  }
+  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 isAudioOnly(filePath) {
+  return [".wav", ".mp3", ".m4a", ".aac", ".flac"].includes(extname(filePath).toLowerCase());
+}
+
+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;
+}

package/vendor/hyperframes/dist/skills/media-use/scripts/transcript-cut.test.mjs

@@ -0,0 +1,117 @@
+import assert from "node:assert/strict";
+import { execFileSync, spawnSync } from "node:child_process";
+import { mkdtempSync, rmSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import test from "node:test";
+import { fileURLToPath } from "node:url";
+
+const SCRIPT = fileURLToPath(new URL("./transcript-cut.mjs", import.meta.url));
+const HAS_FFMPEG =
+  spawnSync("ffmpeg", ["-version"], { stdio: "ignore" }).status === 0 &&
+  spawnSync("ffprobe", ["-version"], { stdio: "ignore" }).status === 0;
+
+const SAMPLE_RATE = 44100;
+// A continuous tone's own slope between samples never exceeds amplitude * 2*pi*f/rate
+// (~2054 for 440Hz at full scale here); a raw splice between two independently-cut
+// points on the same tone lands at two unrelated phases, so an unfaded join jumps far
+// past that. This threshold sits well above normal tone motion and well below a splice.
+const MAX_CONTINUOUS_STEP = 6000;
+const MIN_SUSPICIOUS_ZERO_RUN = 20;
+
+function fixture() {
+  const dir = mkdtempSync(join(tmpdir(), "media-use-transcript-cut-"));
+  return { dir, cleanup: () => rmSync(dir, { recursive: true, force: true }) };
+}
+
+function run(args) {
+  return spawnSync(process.execPath, [SCRIPT, ...args], { encoding: "utf8" });
+}
+
+function readPcm(filePath) {
+  const raw = execFileSync("ffmpeg", [
+    "-hide_banner",
+    "-loglevel",
+    "error",
+    "-i",
+    filePath,
+    "-f",
+    "s16le",
+    "-ac",
+    "1",
+    "-ar",
+    String(SAMPLE_RATE),
+    "-",
+  ]);
+  const samples = new Int16Array(raw.buffer, raw.byteOffset, raw.length / 2);
+  return samples;
+}
+
+test(
+  "keeps a spliced tone continuous at every cut, with no raw phase jump or silence gap",
+  { skip: !HAS_FFMPEG },
+  (t) => {
+    const { dir, cleanup } = fixture();
+    t.after(cleanup);
+
+    const source = join(dir, "tone.wav");
+    execFileSync("ffmpeg", [
+      "-y",
+      "-hide_banner",
+      "-loglevel",
+      "error",
+      "-f",
+      "lavfi",
+      "-i",
+      `sine=frequency=440:duration=6:sample_rate=${SAMPLE_RATE}`,
+      source,
+    ]);
+
+    const transcriptPath = join(dir, "transcript.json");
+    writeFileSync(transcriptPath, JSON.stringify({ words: [{ text: "tone", start: 0, end: 6 }] }));
+
+    const output = join(dir, "out.wav");
+    // Two "ugly" removal ranges: neither aligned to the 440Hz period, so the kept
+    // segments' cut edges land at unrelated phases of the same continuous tone --
+    // exactly the shape that clicks without a fade, and the shape jrusso1020's
+    // review proved this branch never actually fades.
+    const result = run([
+      "--input",
+      source,
+      "--transcript",
+      transcriptPath,
+      "--remove",
+      "1.37-1.83,3.29-3.71",
+      "--out",
+      output,
+      "--json",
+    ]);
+    assert.equal(result.status, 0, result.stderr || result.stdout);
+
+    const samples = readPcm(output);
+    assert.ok(samples.length > SAMPLE_RATE, "expected several seconds of audio");
+
+    let maxStep = 0;
+    let zeroRun = 0;
+    let maxZeroRun = 0;
+    for (let i = 1; i < samples.length; i++) {
+      const step = Math.abs(samples[i] - samples[i - 1]);
+      if (step > maxStep) maxStep = step;
+      if (samples[i] === 0) {
+        zeroRun++;
+        if (zeroRun > maxZeroRun) maxZeroRun = zeroRun;
+      } else {
+        zeroRun = 0;
+      }
+    }
+
+    assert.ok(
+      maxStep <= MAX_CONTINUOUS_STEP,
+      `largest sample-to-sample step was ${maxStep}, expected <= ${MAX_CONTINUOUS_STEP} (a raw, unfaded splice)`,
+    );
+    assert.ok(
+      maxZeroRun < MIN_SUSPICIOUS_ZERO_RUN,
+      `found a run of ${maxZeroRun} consecutive zero samples, expected < ${MIN_SUSPICIOUS_ZERO_RUN} (a priming-silence gap)`,
+    );
+  },
+);