What This Skill Does
Generate speech audio from text using the OpenAI Audio API. Supports multiple voices, output formats, and batch generation for narration, accessibility, and audio content.
When to Use It
- Text-to-speech narration or voiceover
- Accessibility audio generation
- Creating audio prompts or notifications
- Batch speech generation for multiple texts
Requirements
OPENAI_API_KEYenvironment variable- Bundled CLI:
scripts/text_to_speech.py
Features
- Multiple built-in voices with different characteristics
- Various output formats (MP3, WAV, etc.)
- Speed control for narration pacing
- Batch mode for processing multiple texts
Limitations
- Custom voice creation is out of scope
- Real-time streaming not supported through this skill