speech
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (scripts/text_to_speech.py) with built-in voices and require OPENAI_API_KEY for live calls. Custom voice creation is out of scope.
Pinned to revision 4e4fe02df5f4, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/speech/SKILL.md
- skills/speech/LICENSE.txt
- skills/speech/agents/openai.yaml
- skills/speech/assets/speech-small.svg
- skills/speech/assets/speech.png
- skills/speech/metadata.json
- skills/speech/references/accessibility.md
- skills/speech/references/audio-api.md
- skills/speech/references/cli.md
- skills/speech/references/codex-network.md
- skills/speech/references/ivr.md
- skills/speech/references/narration.md
- skills/speech/references/prompting.md
- skills/speech/references/sample-prompts.md
- skills/speech/references/voice-directions.md
- skills/speech/references/voiceover.md
- skills/speech/scripts/text_to_speech.py
Every link opens the file at its source, pinned to the revision this page describes.