Subvert generates subtitles, chapters, and summaries from video files using OpenAI's Whisper and ChatGPT models. It targets users who need to quickly process video content for accessibility or content creation, offering automated transcription and metadata generation.

How It Works

The application extracts audio from video files using FFmpeg, transcribes it via OpenAI's Whisper API into VTT format, and then uses ChatGPT to generate chapter markers and a concise summary. This pipeline automates tedious video processing tasks, leveraging powerful AI models for efficient content analysis.

Quick Start & Requirements

• Install via Docker: docker run -it -p 80:8080 -e OPENAI_API_KEY=sk-123abc aschmelyun/subvert
• Requires Docker and an OpenAI API key.
• Configuration options include UPLOAD_MAX_FILESIZE and MEMORY_LIMIT via environment variables.
• Alternative: Run from source with PHP 8.1+ and npm installed (./startup.sh in src directory).

Highlighted Details

• Generates subtitles, chapters, and summaries.
• Utilizes OpenAI Whisper for transcription and ChatGPT for summarization/chaptering.
• Self-contained Docker image for easy deployment.
• Configurable upload and memory limits.

Maintenance & Community

• Marked as a work-in-progress with an invitation to create issues for bugs.
• No specific community links (Discord, Slack) or notable contributors mentioned.

Licensing & Compatibility

• MIT License (MIT).
• Permissive license suitable for commercial use and integration with closed-source projects.

Limitations & Caveats

• The project is explicitly stated as a work-in-progress.
• Currently only exposes the insecure HTTP port :80.