Function transcribeAudio

packages/cli/src/commands/transcribe.ts:216–303

(
  inputPath: string,
  dir: string,
  opts: { model?: string; language?: string; json?: boolean; optional?: boolean },
)

// ---------------------------------------------------------------------------

async function transcribeAudio(
  inputPath: string,
  dir: string,
  opts: { model?: string; language?: string; json?: boolean; optional?: boolean },
): Promise<void> {
  const { transcribe } = await import("../whisper/transcribe.js");
  const { loadTranscript, patchCaptionHtml, stripBeforeOnset } =
    await import("../whisper/normalize.js");

  const model = opts.model ?? DEFAULT_MODEL;
  const spin = opts.json ? null : clack.spinner();
  spin?.start(`Transcribing with ${c.accent(model)}...`);

  try {
    const result = await transcribe(inputPath, dir, {
      model,
      language: opts.language,
      onProgress: spin ? (msg) => spin.message(msg) : undefined,
    });

    let { words } = loadTranscript(result.transcriptPath);

    if (result.speechOnsetSeconds != null) {
      const before = words.length;
      words = stripBeforeOnset(words, result.speechOnsetSeconds);
      const stripped = before - words.length;
      if (stripped > 0 && !opts.json) {
        spin?.message(
          `Stripped ${stripped} words before speech onset at ${result.speechOnsetSeconds.toFixed(1)}s`,
        );
      }
    }

    writeFileSync(result.transcriptPath, JSON.stringify(words, null, 2));
    patchCaptionHtml(dir, words);

    if (opts.json) {
      console.log(
        JSON.stringify({
          ok: true,
          model,
          wordCount: words.length,
          durationSeconds: result.durationSeconds,
          speechOnsetSeconds: result.speechOnsetSeconds,
          transcriptPath: result.transcriptPath,
        }),
      );
    } else {
      const onsetNote =
        result.speechOnsetSeconds != null
          ? ` — speech detected at ${result.speechOnsetSeconds.toFixed(1)}s`
          : "";
      spin?.stop(
        c.success(
          `Transcribed ${c.accent(String(words.length))} words (${result.durationSeconds.toFixed(1)}s${onsetNote})`,
        ),
      );
    }