Skip to content

JaimeJunr/claude-code-frontend-skills / plugins/hyperframes/skills/media-use

media-use

Verified

Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.

FileKindSize
.gitignoreother17 B
SKILL.mdskill md5.3 KB
audio/assets/sfx/CREDITS.mdmarkdown1.2 KB
audio/assets/sfx/chime.mp3binary26.7 KB
audio/assets/sfx/click-soft.mp3binary11.4 KB
audio/assets/sfx/click.mp3binary11.4 KB
audio/assets/sfx/error.mp3binary50.6 KB
audio/assets/sfx/glitch-1.mp3binary82.4 KB
audio/assets/sfx/glitch-2.mp3binary109.5 KB
audio/assets/sfx/glitch-3.mp3binary96.8 KB
audio/assets/sfx/impact-bass-1.mp3binary66.1 KB
audio/assets/sfx/impact-bass-2.mp3binary81.0 KB
audio/assets/sfx/key-press.mp3binary3.8 KB
audio/assets/sfx/manifest.jsonconfig3.6 KB
audio/assets/sfx/notification.mp3binary76.7 KB
audio/assets/sfx/ping.mp3binary25.8 KB
audio/assets/sfx/pop.mp3binary22.5 KB
audio/assets/sfx/riser.mp3binary313.5 KB
audio/assets/sfx/sparkle.mp3binary56.3 KB
audio/assets/sfx/typing.mp3binary26.2 KB
audio/assets/sfx/whoosh-cinematic.mp3binary173.3 KB
audio/assets/sfx/whoosh-short.mp3binary18.0 KB
audio/assets/sfx/whoosh.mp3binary18.0 KB
audio/references/bgm.mdmarkdown7.9 KB
audio/references/captions/authoring.mdmarkdown9.2 KB
audio/references/captions/motion.mdmarkdown5.4 KB
audio/references/captions/transcript-handling.mdmarkdown5.3 KB
audio/references/remove-background.mdmarkdown8.3 KB
audio/references/requirements.mdmarkdown4.7 KB
audio/references/sfx.mdmarkdown4.0 KB
audio/references/transcribe.mdmarkdown2.8 KB
audio/references/tts-to-captions.mdmarkdown1.7 KB
audio/references/tts.mdmarkdown13.9 KB
audio/scripts/audio.mjsscript15.2 KB
audio/scripts/audio.test.mjsscript8.4 KB
audio/scripts/carve.mjsscript20.1 KB
audio/scripts/carve.test.mjsscript12.2 KB
audio/scripts/extract-audio-data.pyscript7.1 KB
audio/scripts/gemini-pipeline.test.mjsscript4.8 KB
audio/scripts/heygen-tts.mjsexecutablescript4.3 KB
audio/scripts/heygen-tts.test.mjsscript1.4 KB
audio/scripts/heygen-voice.mjsscript3.8 KB
audio/scripts/heygen-voice.test.mjsscript8.3 KB
audio/scripts/lib/audio-carve.mjsscript16.6 KB
audio/scripts/lib/audio-meta.mjsscript1.1 KB
audio/scripts/lib/audio-meta.test.mjsscript4.5 KB
audio/scripts/lib/bgm-volume.mjsscript236 B
audio/scripts/lib/bgm.mjsscript11.5 KB
audio/scripts/lib/bgm.test.mjsscript4.7 KB
audio/scripts/lib/concurrency.mjsscript527 B
audio/scripts/lib/concurrency.test.mjsscript1.6 KB
audio/scripts/lib/gemini-auth.mjsscript1.6 KB
audio/scripts/lib/gemini-auth.pyscript1.9 KB
audio/scripts/lib/gemini-auth.test.mjsscript3.0 KB
audio/scripts/lib/gemini-auth_test.pyscript4.3 KB
audio/scripts/lib/gemini-tts.mjsscript5.0 KB
audio/scripts/lib/gemini-tts.test.mjsscript9.2 KB
audio/scripts/lib/heygen.mjsscript14.3 KB
audio/scripts/lib/heygen.test.mjsscript22.9 KB
audio/scripts/lib/main-module.mjsscript479 B
audio/scripts/lib/media-record.mjsscript5.1 KB
audio/scripts/lib/media-record.test.mjsscript12.6 KB
audio/scripts/lib/openverse.mjsscript4.9 KB
audio/scripts/lib/project-path.mjsscript2.2 KB
audio/scripts/lib/project-path.test.mjsscript3.0 KB
audio/scripts/lib/python.mjsscript4.6 KB
audio/scripts/lib/python.test.mjsscript7.8 KB
audio/scripts/lib/recording.mjsscript4.4 KB
audio/scripts/lib/sfx.mjsscript7.2 KB
audio/scripts/lib/sfx.test.mjsscript11.6 KB
audio/scripts/lib/tts.cleanup.test.mjsscript7.0 KB
audio/scripts/lib/tts.mjsscript18.6 KB
audio/scripts/lib/tts.spawn.test.mjsscript6.0 KB
audio/scripts/lib/tts.test.mjsscript10.2 KB
audio/scripts/lib/voice-credit.mjsscript686 B
audio/scripts/lib/voice-credit.test.mjsscript946 B
audio/scripts/lyria-recipe.pyscript4.9 KB
audio/scripts/recording.test.mjsscript9.2 KB
audio/scripts/trusted-program.test.mjsscript3.4 KB
audio/scripts/trusted_program.pyscript2.8 KB
audio/scripts/wait-bgm.mjsscript6.1 KB
audio/scripts/wait-bgm.test.mjsscript8.0 KB
luts/README.mdmarkdown1.1 KB
luts/index.jsonconfig2.0 KB
references/audio.mdmarkdown3.5 KB
references/grading.mdmarkdown7.0 KB
references/heygen.mdmarkdown11.8 KB
references/local.mdmarkdown2.6 KB
references/media-treatment-recipes.mdmarkdown35.0 KB
references/media-treatments.mdmarkdown13.8 KB
references/memory.mdmarkdown3.7 KB
references/meta.mdmarkdown6.4 KB
references/mixing.mdmarkdown4.5 KB
references/operations.mdmarkdown15.8 KB
references/resolve.mdmarkdown9.9 KB
references/setup-providers.mdmarkdown9.1 KB
references/telemetry-dashboard.mdmarkdown4.1 KB
scripts/audio-duck.mjsscript4.0 KB
scripts/compatibility.test.mjsscript1.6 KB
scripts/dither.mjsscript9.8 KB
scripts/dither.test.mjsscript4.6 KB
scripts/eval.mjsscript14.6 KB
scripts/lib/config-lock.mjsscript1.5 KB
scripts/lib/credit-limit.mjsscript2.0 KB
scripts/lib/cutlist.mjsscript6.2 KB
scripts/lib/duck.mjsscript3.8 KB
scripts/lib/error-diffusion.mjsscript6.5 KB
scripts/lib/index-gen.mjsscript2.0 KB
scripts/lib/manifest.mjsscript10.6 KB
scripts/lib/media-fetch.mjsscript2.8 KB
scripts/lib/media-home.mjsscript730 B
scripts/lib/npx-sync.mjsscript3.2 KB
scripts/lib/parakeet-words.mjsscript1.1 KB
scripts/lib/prefs-store.mjsscript6.8 KB
scripts/lib/recipe-store.mjsscript13.0 KB
scripts/lib/telemetry.mjsscript8.8 KB
scripts/lib/telemetry.test.mjsscript3.0 KB
scripts/lib/transcriptCutFade.mjsscript911 B
scripts/lib/windows-exe-search.mjsscript640 B
scripts/lib/words.mjsscript728 B
scripts/prefs.mjsscript2.3 KB
scripts/recipe.mjsscript3.8 KB
scripts/resolve-plugin.test.mjsscript3.2 KB
scripts/resolve.mjsscript1.4 KB
scripts/transcribe.mjsscript8.0 KB
scripts/transcribe.test.mjsscript7.7 KB
scripts/transcript-cut.mjsscript10.1 KB
scripts/transcript-cut.test.mjsscript9.6 KB

scripts/transcribe.mjs

View on GitHub
#!/usr/bin/env node

import "./lib/windows-exe-search.mjs";
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() {
  // An override with a folder in it means the caller's folder; the runner itself starts elsewhere.
  const override = process.env.HYPERFRAMES_PARAKEET;
  for (const p of [
    override && /[\\/]/.test(override) ? resolve(override) : override,
    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})`,
    );
}

// parakeet-mlx reads a model id as a folder when one exists in its working directory, so it runs in
// the home folder. A model written as a relative path (./ or ../) still means the caller's folder.
function modelFor(model, cwd = process.cwd()) {
  return /^\.\.?[\\/]/.test(model) ? resolve(cwd, model) : model;
}

function runParakeet(runner) {
  const workDir = mkdtempSync(join(tmpdir(), "media-use-asr-"));
  try {
    execFileSync(
      runner,
      [
        inputPath,
        "--model",
        modelFor(args.model),
        "--output-format",
        "json",
        "--output-dir",
        workDir,
      ],
      { cwd: homedir(), 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);
}
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall