Multimodal AI

Vision and audio AI integration. Image analysis, transcription, text-to-speech.

Quick Start

npx ai-multimodal vision ./image.png "Describe this"

What It Does

• Analyze images with GPT-4 Vision
• Extract text from images (OCR)
• Transcribe audio with Whisper
• Generate speech from text

Usage

# Vision
npx ai-multimodal vision ./photo.jpg "What's in this?"

# OCR
npx ai-multimodal ocr ./screenshot.png

# Transcribe
npx ai-multimodal transcribe ./audio.mp3

# Text to speech
npx ai-multimodal tts "Hello" ./output.mp3

Part of the LXGIC Dev Toolkit

One of 110+ free developer tools from LXGIC Studios.

• GitHub: https://github.com/lxgicstudios
• Twitter: https://x.com/lxgicstudios
• Website: https://lxgicstudios.com

License

MIT. Free forever.