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.; pctx: pctx sits between AI agents and MCP servers, aggregating multiple upstream MCP servers, handling authentication, and exposing tools through a unified Code Mode interface. It replaces sequential tool calling with code execution, resulting in significant token reduction. It supports multiple installation methods and provides Python SDK for agent development.
Meeting transcription with speaker labels, timestamps, and punctuation
Building AI agents that need to interact with multiple MCP servers efficiently