andraz/ragtitles
Optimize Subtitles for RAG Ingestion
This tool helps anyone working with video content to efficiently prepare YouTube subtitles for use with large language models (LLMs). It takes standard YouTube VTT subtitle files and converts them into a concise, timestamped format, making them ready to be fed directly into an LLM for tasks like summarization, content analysis, or generating Q&A. Content creators, researchers, and anyone analyzing video transcripts will find this useful.
Available on npm.
Use this if you need to transform verbose YouTube subtitles into a streamlined, token-optimized format for efficient processing by RAG systems or direct LLM prompting.
Not ideal if you primarily need to edit subtitles for human readability or video accessibility, as this tool focuses on optimizing for machine ingestion.
Stars
11
Forks
—
Language
TypeScript
License
MIT
Category
Last pushed
Feb 14, 2026
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/andraz/ragtitles"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVIDIA-AI-Blueprints/video-search-and-summarization
Blueprint for Ingesting massive volumes of live or archived videos and extract insights for...
kaya70875/ytfetcher
⚡ Build structured YouTube datasets at scale — effortlessly fetch transcripts and rich metadata...
HKUDS/VideoRAG
[KDD'2026] "VideoRAG: Chat with Your Videos"
jonaskahn/asktube
AskTube - An AI-powered YouTube video summarizer and QA assistant powered by Retrieval Augmented...
wassim249/YT-Navigator
YT Navigator: AI-powered YouTube content explorer that lets you search and chat with channel...