Speech, summaries, retrieval, and question answering stay on your computer

Local-First AI & Privacy

Run speech recognition, local language models, embeddings, and the meeting knowledge index on your own machine instead of sending meeting content to a remote inference API.

Key Capabilities

One privacy boundary for the whole workflow

Privacy is not only about recording. RecapFox keeps transcription, summarization, search indexing, semantic retrieval, and meeting Q&A inside the local desktop workflow.

Network access is separate from inference

Model downloads and application updates can require network access, but meeting content does not need to be sent to a hosted model service for transcription, summarization, search, or Q&A.

Learn the workflow

Local-first architecture: Meeting-content transcription, language-model reasoning, embeddings, and retrieval are designed to run locally rather than requiring a hosted inference API.