speech

Topics in the source

• Speech Generation Skill
• When to use
• Decision tree (single vs batch)
• Workflow
• Temp and output conventions
• Dependencies (install if missing)
• Environment
• Defaults & rules

Generate spoken audio for the current project (narration, product demo voiceover, IVR prompts, accessibility reads). OpenAI remains the default with gpt-4o-mini-tts-2025-12-15; Atlas Cloud is available only when the user explicitly selects it. Prefer the bundled CLIs for deterministic, reproducible runs. Generate a single spoken clip from text Generate a batch of prompts (many lines, many files) If the user provides multiple lines/prompts or wants many outputs -> batch Else -> single 1. Decide intent: single vs batch (see decision tree above). 2. Collect inputs up front: exact text (verbatim), desired voice, delivery style, format, and any 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 scripts/texttospeech.py for the default OpenAI path, or scripts/atlastexttospeech.py only when Atlas Cloud was selected (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/r

This is an excerpt. Refer to the complete source and its current requirements.