$ show octimot/StoryToolkitAI
StoryToolkitAI is a video editing toolkit that leverages AI to enhance post-production workflows. It operates in dual modes (GUI and CLI) with core functionality centered around transcription, semantic search, speaker diarization, and integration with DaVinci Resolve Studio. The application enables users to transcribe media files, search content using natural language, generate stories via LLM assistance, and export to professional editing formats (EDL, XML, Fountain). Key architectural elements include a plugin-based system for LLM providers, a persistent task queue with dependency tracking for CPU/GPU workloads, and project-based file linking for unified search across media assets. The tool emphasizes local processing with optional external API usage for advanced features.
The LLM identified 2 files worth highlighting for reuse:
Implements a thread-safe task queue with dependency tracking (e.g., ensuring transcription completes before speaker detection) and persistence to disk for crash recovery. Workers are allocated per device (CPU/CUDA) to manage GPU memory. This pattern is reusable in any application requiring background task processing with complex dependencies.
Uses Pydantic models to validate media ingestion settings (timecodes, frame rates, intervals, etc.) providing type-safe and domain-specific configuration management. This pattern ensures robust handling of media metadata and can be extracted for use in other media processing applications.