Speech Generation Skill

Generate spoken audio for the current project (narration, product demo voiceover, IVR prompts, accessibility reads). Defaults to gpt-4o-mini-tts-2025-12-15 and built-in voices, and prefers the bundled CLI for deterministic, reproducible runs.

Workflow

1. Decide intent: single clip or batch (multiple lines/prompts → batch).
2. Collect inputs: exact text (verbatim), voice, delivery style, format, constraints.
3. If batch: write a temporary JSONL under tmp/ (one job per line), run once, then delete the JSONL.
4. Augment instructions into a short labeled spec without rewriting the input text.
5. Run the bundled CLI (scripts/text_to_speech.py) with sensible defaults (see references/cli.md).
6. For important clips, validate: intelligibility, pacing, pronunciation, and adherence to constraints.
7. Iterate with a single targeted change (voice, speed, or instructions), then re-check.
8. Save/return final outputs and note the final text + instructions + flags used.

Temp and output conventions

• Use tmp/speech/ for intermediate files (for example JSONL batches); delete when done.
• Write final artifacts under output/speech/ when working in this repo.
• Use --out or --out-dir to control output paths; keep filenames stable and descriptive.