speech - Generate spoken audio from text using OpenAI API
Convert text to speech for narrations, voiceovers, IVR prompts, or accessibility reads via bundled CLI or OpenAI Audio API.
Tags
Updated: 2026-03-24Capabilities
Typical Inputs
Typical Outputs
What this skill does
- generate single spoken clip
- generate batch prompts
- create audio files
- validate audio output
- save audio files
Inputs
- input text
- voice selection
- delivery style instructions
- output format
- OPENAI_API_KEY
Outputs
- audio files
- JSONL batch files
Requirements
- Python environment
- openai Python package
- OPENAI_API_KEY