# octimot/StoryToolkitAI

An editing tool that uses AI to transcribe, understand content and search for anything in your footage,  integrated with ChatGPT and other AI models

Repository: https://github.com/octimot/StoryToolkitAI
Canonical: https://ross.abutalabs.com/products/storytoolkitai
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: ai, davinci-resolve, editing, film-editing, filmmaking, sentence-transformers, speech-recognition, video-processing, chatgpt, gpt
Last push: 2026-07-28T06:37:10+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 8, longevity 100
- inputs: {"age_days": 1434, "days_push": 36, "days_rel": 559, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1006, forks 86 (observed 2026-08-28T04:03:11.913760+00:00)

## What it is
StoryToolkitAI is a desktop film editing tool that transcribes, indexes, and semantically searches video footage locally, using speech recognition and sentence transformers. It integrates with LLMs like OpenAI GPT, Ollama, and DeepSeek to generate stories and selections, and exports to DaVinci Resolve via EDL/XML.

## Use cases
- search my footage by meaning instead of exact words
- automatically transcribe interview footage locally for free
- have AI pick the best takes and build a story from my clips
- import AI-generated selections into DaVinci Resolve
- generate SRT subtitles from video files
- index a large video archive so I can find any scene later

## When to choose
- you edit film/documentary footage and need semantic search across hours of video
- you want local, free transcription and translation without uploading footage
- you use DaVinci Resolve Studio and want AI-assisted timeline marking and story building
- you want to chat with an LLM about your own footage content

## When to avoid
- you need a fully automated one-click video editor with no manual review
- you don't use DaVinci Resolve and only need simple transcription (dedicated tools may be lighter)
- you need real-time or streaming transcription during live recording
- your workflow depends on cloud-only processing with zero local setup

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, video-processing, search-engine, nlp, llm-inference, rag
- domain: artificial-intelligence, large-language-models, media, developer-tools
- platform: windows, python
- tags: davinci-resolve, film-editing, transcription, video-indexing, semantic-search, story-editor, chatgpt-integration, ollama, video, macos, desktop

## Member repositories
- octimot/StoryToolkitAI (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:11.913760+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:12:58.131679+00:00, confidence not recorded.
  - readme: https://github.com/octimot/StoryToolkitAI (fetched 2026-08-28T04:03:11.913760+00:00, sha 9a8ee311ba02)
- Data as of 2026-08-30T08:39:29.467469+00:00.