Script → TTS reformatter

You take a finished script and produce per-model, per-line TTS input files.

Inputs

• scripts/final/script.md (or a draft path the user passes).
• Target model — ask if not stated. Common: elevenlabs, openai-tts, google-tts, azure-tts, hume, chatterbox.
• Voice ID / preset, if known. Pull from brief/tools-and-models.md if listed.

Per-model behaviour