I built AmicoScript: A local-first Whisper UI with Speaker Diarization and Ollama integration for summaries.

AmicoScript is a local-first, FastAPI-based application that combines OpenAI's Whisper for accurate speech-to-text transcription with Speaker Diarization to identify and separate different speakers within an audio file. It integrates with Ollama, allowing users to leverage local large language models to generate concise summaries from transcribed audio — all without relying on cloud services. This privacy-focused, self-hosted tool runs entirely on consumer GPUs, making it well-suited for sensitive information or environments with limited internet access.

Related

• What Your Local LLM Actually Sees: Debugging Ollama Traffic in Quarkus with mitmproxy
• MinusPod: Fully Self-Hostable Automatic Podcast Ad Removal.
• Use the Same Model Across Ollama, LM Studio, Jan, and your Favorite Local AI Apps
• Alternative to NotebookLM with no data limits

Source: local-ai