Whisper
Speech recognition service wrapping OpenAI's Whisper models, transcribing and translating audio across many languages with timestamps, served over an HTTP endpoint.
A sophisticated content analysis and organization platform that transforms unstructured media libraries into searchable, queryable knowledge systems. Whisper transcribes thousands of videos into accurate text representations, creating a foundation for content understanding and searchability. Supabase stores both the structured metadata and vector embeddings of transcripts, enabling complex queries across your entire content library. Qdrant provides semantic search capabilities that can find videos based on topics, themes, or concepts even when specific keywords aren't mentioned. Neo4j maps relationships between content pieces, identifying recurring themes, guest appearances, and topic evolution over time. AnythingLLM creates an interactive interface where you can ask natural language questions about your content archive and receive comprehensive answers that draw from across your entire library. This system addresses the critical challenge faced by prolific content creators who have valuable insights buried in thousands of hours of video but lack efficient ways to discover, analyze, and repurpose that intellectual capital.
Speech recognition service wrapping OpenAI's Whisper models, transcribing and translating audio across many languages with timestamps, served over an HTTP endpoint.
Backend platform assembled around PostgreSQL, adding generated REST and GraphQL APIs, authentication, authorisation through row-level security, file storage and realtime change streams.
Vector database written in Rust, pairing dense and sparse vectors with structured payloads so that metadata filters and nearest-neighbour search are resolved together in a single query.
Graph database built on the property graph model and the Cypher query language, used for knowledge graphs, network analysis and relationship-heavy queries that join badly in SQL.
Retrieval-augmented chat workspace bundling document ingestion, embedding, vector storage and multi-provider model connectivity into one container. Answers cite the source passages they were drawn from.
Workflow automation platform with 400+ service integrations, extensible in JavaScript. Runs event-driven and scheduled flows across APIs, databases and model endpoints.