ScreenPal Video Transcriber

Acerca de

This Kiro CLI custom agent offers a privacy-first solution for analyzing ScreenPal videos. It leverages local AI models, including OpenAI Whisper for high-quality audio transcription and Vision-Language Models (VLMs) like Moondream2 via Ollama for semantic visual analysis. The agent seamlessly integrates audio and visual insights, providing a rich, timestamped transcript that captures both spoken content and on-screen activity, all processed securely on your local machine.

Características Principales

• Audio Transcription with Whisper
• Visual Content Analysis with Local VLMs
• Privacy-First Local Processing
• Temporal Context and Scene Detection
• ScreenPal URL Validation
• 0 GitHub stars

Casos de Uso

• Automating comprehensive transcription of ScreenPal videos
• Performing privacy-focused visual and audio analysis of video content
• Enhancing knowledge bases with detailed, timestamped video insights