openai-tts

Overview: Use OpenAI's Text-to-Speech API to generate high-quality speech from text. This skill provides a simple CLI interface for customization and flexibility.

Key Features:

• Customizable voices (6 options)
• Choose from two models (fast or high-quality)
• Select from various audio formats (MP3, OPUS, AAC, FLAC, WAV, PCM)
• Adjust speech speed (0.25-4.0)

How It Works: The skill uses the curl binary to send a request to OpenAI's /v1/audio/speech endpoint, which generates the speech audio. You can customize the voice, model, format, and speed using flags.

Use Cases:

• Create automated voice responses for chatbots or IVRs
• Generate audio content for podcasts, audiobooks, or videos
• Experiment with different voices and styles for creative projects