An LLM-powered desktop and CLI tool for video subtitles: speech recognition, sentence segmentation, correction, translation and burning subtitles into video.
octimot/StoryToolkitAI
A local-first film editing tool that transcribes and indexes footage, enables semantic search, and uses LLMs to help build stories for DaVinci Resolve.
Open-source alternative to:Adobe Premiere Pro
- Stars
- 1,048
- Forks
- 88
- Open issues
- 40
- Last commit
- 3 months ago
What is it?
StoryToolkitAI is a film editing assistant that helps editors understand and search their footage. It runs locally on the user's machine and provides automatic transcription and translation to English, indexes video scenes, and lets you search content by meaning rather than exact words.
The tool connects to large language models such as OpenAI GPT-4, ollama, vLLM and LM Studio, so users can chat about their content, generate ideas, or ask the AI to select clips and assemble stories. Selections and stories can be exported as EDL, XML or Fountain for use in editing software.
It integrates with DaVinci Resolve Studio 18+, allowing users to navigate timelines through the transcript, search timeline markers with AI, and import subtitles into the media bin. Transcripts can be exported as SRT, TXT, AVID DS or Fusion Text nodes.
Key features
- 01Full video indexing and semantic search without exact keywords
- 02Local automatic transcription and translation to English
- 03Works with OpenAI, ollama, vLLM and LM Studio models
- 04Export of selections and stories as EDL, XML or Fountain
- 05Speaker detection and transcript groups
- 06Deep integration with DaVinci Resolve Studio 18+
Use cases
- Finding specific quotes or moments across long interview footage
- Drafting rough cuts or selects with an LLM from transcripts
- Generating subtitles and translations for video projects
- Navigating and searching DaVinci Resolve timelines through transcripts
Topics
FAQ
- What is StoryToolkitAI?
- A local-first film editing tool that transcribes and indexes footage, enables semantic search, and uses LLMs to help build stories for DaVinci Resolve. StoryToolkitAI is a film editing assistant that helps editors understand and search their footage. It runs locally on the user's machine and provides automatic transcription and translation to English, indexes video scenes, and lets you search content by meaning rather than exact words.
- Is StoryToolkitAI free to use? What license does it have?
- StoryToolkitAI is open source under the GPL-3.0 license. Check the license terms before using it in commercial products.
- Is StoryToolkitAI still maintained?
- Updated within 6 months. The last commit to StoryToolkitAI was on Jul 28, 2026.
- What can I use StoryToolkitAI for?
- Finding specific quotes or moments across long interview footage Drafting rough cuts or selects with an LLM from transcripts Generating subtitles and translations for video projects Navigating and searching DaVinci Resolve timelines through transcripts
- Where can I get StoryToolkitAI?
- The source code and installation instructions are on GitHub: https://github.com/octimot/StoryToolkitAI
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Local-first AI subtitle generator that runs offline and plugs into DaVinci Resolve, Premiere Pro and After Effects.
A community-curated open-source library of prompts for AI chat models, with a website, CSV/Hugging Face datasets, CLI and MCP server integration.
Local-first AI memory system that stores conversation history verbatim and retrieves it with semantic search, exposed as an MCP server and CLI.
A low-level Python framework for building stateful, long-running agents with durable execution, human-in-the-loop and memory.
Self-hostable AI second brain that answers questions from the web and your own documents, with custom agents and scheduled automations.