A TikTok video processing server based on the MCP protocol, supporting watermark-free video download, audio extraction, and text conversion functions.

Speech MCP is a voice interaction extension designed for Goose, providing real-time voice recognition, text-to-speech, and audio visualization functions.

This project expands the video speech recognition function. It originally only supported the local Whisper model, and now it newly supports the online speech recognition services of CapCut and Bcut, providing a flexible multi - service selection architecture.

A high-performance speech recognition MCP server based on Faster Whisper, providing efficient audio transcription capabilities, supporting batch processing, multiple model sizes, and multiple output formats.

Speech MCP is a voice interaction extension designed for Goose, providing real-time voice recognition, high-quality text-to-speech, multilingual support, and a modern audio visualization interface. It supports multi-character dialogue generation and audio transcription functions.

The MCP Speaker Diarization and Recognition System is a complete solution integrating GPU-accelerated speaker separation, speech recognition, emotion detection, and a web interface. It combines the speaker separation of pyannote.audio with the faster-whisper transcription technology, supporting persistent speaker recognition (one-time registration, permanent recognition), dual-detector emotion analysis (combining general AI and personalized voiceprints), real-time stream processing, REST API, and MCP server, and is designed for AI intelligent agent integration and hobby projects.

The ASR MCP server is an automatic speech recognition service based on the Whisper engine, providing the speech synthesis function through the MCP tool for easy application integration.