FunASR: FunASR is a fundamental end-to-end speech recognition toolkit. It offers industrial-grade speech recognition, being 170x faster than Whisper, supporting over 50 languages, and integrating features like speaker diarization, emotion detection, and streaming.; pi-mcp-adapter: Pi MCP Adapter allows you to use MCP servers with Pi while avoiding token bloat. It lazily connects servers only when needed, caches tool metadata, and provides a single proxy tool to reduce context usage. It supports various lifecycle modes, direct tools, and interactive configuration.
Meeting transcription with speaker labels, timestamps, and punctuation
Access databases via MCP database servers