Function wordsToCues

packages/cli/src/whisper/normalize.ts:367–403

(words: Word[], opts: WordsToCuesOptions = {})

}

export function wordsToCues(words: Word[], opts: WordsToCuesOptions = {}): Cue[] {
  // Phrase-level transcripts (imported .srt/.vtt cues) must keep their existing
  // cue boundaries — re-grouping would merge distinct captions and lose timing.
  // The caller can force this via `preGrouped`; otherwise infer it from the data
  // (any entry containing internal whitespace is a multi-word phrase, so the
  // whole transcript is phrase-level rather than word-level whisper output).
  const preGrouped = opts.preGrouped ?? words.some((w) => /\s/.test(w.text.trim()));
  if (preGrouped) return entriesToCues(words);

  const maxChars = opts.maxChars ?? 42;
  const maxGap = opts.maxGap ?? 0.8;
  const cues: Cue[] = [];
  let current: Cue | undefined;

  const flush = (): void => {
    pushCue(cues, current);
    current = undefined;
  };

  for (const word of words) {
    const text = word.text.trim();
    if (!text) continue;

    if (current && !breaksCue(current, word, text, maxChars, maxGap)) {
      current.text = joinTokens(current.text, text);
      current.end = word.end;
    } else {
      flush();
      current = { text, start: word.start, end: word.end };
    }

    if (endsSentence(text)) flush();
  }

  flush();
  return cues;
}

export function formatSrt(words: Word[], opts?: WordsToCuesOptions): string {
  const cues = wordsToCues(words, opts);