AI Speech Generation
Generates high-quality spoken audio for narrations, demos, and accessibility using OpenAI's text-to-speech models.
This skill empowers developers to generate AI-driven voiceovers and audio prompts directly within their project workflow. By leveraging the OpenAI Audio API and the latest GPT-4o-mini-TTS models, it handles everything from single clips for product demos to complex batch processing for IVR systems and accessibility reads. It includes a built-in CLI for deterministic output, supports instruction augmentation for fine-tuning pacing and tone, and enforces best practices for pronunciation and professional delivery while managing local file organization and API rate limits.
Características Principales
01Fine-tuned control over voice affect, tone, pacing, and emphasis
02Automated CLI-based generation with local file management
0316 GitHub stars
04Batch processing for multiple audio prompts via JSONL
05Built-in support for high-quality voices like Cedar and Marin
06Standardized templates for narration, IVR, and accessibility
Casos de Uso
01Creating professional narrations for product demo videos
02Generating batch audio prompts for IVR and phone systems
03Producing accessibility reads and audiobooks from text content