tesseron: Tesseron allows live applications to declare typed actions using Zod-style builders, which MCP-compatible AI agents can invoke as tools over WebSocket. It provides a click-to-connect handshake, no browser automation, and capabilities like confirmation, elicitation, and sampling. The MCP gateway bundles with a Claude Code plugin for easy setup.; 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.
Building AI-driven web apps where an agent directly manipulates UI state
Meeting transcription with speaker labels, timestamps, and punctuation