Show HN: Castrag – transcribe and semantically search a large podcast archive

Category: ai-ml

Tags: podcast, transcription, semantic-search, rag, openai

Score: 5.8/10 (Innovation: 5, Technical: 5, Documentation: 7, Utility: 6)

Castrag is a Python pipeline for transcribing, summarizing, embedding, and querying large podcast archives using OpenAI APIs. It offers a resumable, stage-based workflow that handles transcription, semantic search, and RAG-based Q&A, making large audio archives searchable without a vector database.

Target audience: data engineers and developers working with audio archives

Repository: https://github.com/snowmac/castrag · Python · MIT · 1 stars

View on Hacker News