MCP servers and skills: search, filter by where they run, and compare.
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
SkillMIT★ 21kNo key
Agent skill for multi-speaker meeting & podcast transcription — FunASR (Paraformer/SenseVoice/Whisper) + MiMo-V2.5-ASR + CAM++ speaker diarization + LLM cleanup. 99 languages, GPU & CPU. Works with Cl
SkillMIT★ 11No key
MCPServer is a Python-based server that leverages Alibaba's FunASR library to provide speech processing services through the FastMCP framework.
SkillMIT★ 3Few starsNo key
Voice channel for AI agents. Multi-model TTS (Kokoro, Voxtral, Chatterbox, Spark) with queue-aware output, barge-in detection, and turn-taking. Python.
SkillMIT★ 4Few starsNo key
Claude Code skill for MLX-Audio: TTS, STT, and speech-to-speech on Apple Silicon
SkillMIT★ 3Few starsNo key
Professional video editing skill for Hermes Agent — AI captioning, silence removal, scene detection, stabilisation, smart reframing, and more. All free and open source.
SkillMIT★ 7No key
Offline speech-to-text & speaker diarization for AI agents — Whisper ASR + MCP server + CLI + Python bindings, fully on-device, no cloud | 离线语音识别与说话人分离,Agent 开箱即用
PythonMIT★ 3Few starsNo key
AI long-video transcription skill for Douyin, Bilibili multi-part, and local media — transcripts, subtitles, timestamps, and summaries
SkillMIT★ 3Few starsNo key
ESP-IDF firmware projects for the Waveshare ESP32-C6-Touch-AMOLED-1.8 — built with an agentic-first workflow using Claude Code. Includes MCP canvas, baby cry detection, IMU toy, music synth, BLE mesh
SkillMIT★ 5No key
Voice chatbot with voice+screen output to show that "not everything needs to be spoken"
SkillMIT★ 7No key
Push-to-talk TTS/STT voice MCP assistant with local and cloud speech options.
PythonMIT★ 4Few starsNo key
Agent Skill: build phone-call voice agents on Gemini Live with LiveKit (Cloud/self-hosted), SIP trunking or WebSocket media streams (Twilio, Exotel, Plivo, Telnyx, Vonage)
SkillMITFew starsNo key
Codex skill for building and debugging open-source realtime voice agents with Hugging Face Speech-to-Speech, OpenAI Realtime, STT, LLM and TTS.
SkillMIT★ 2Few starsNo key
Agent Skill — offline audio/video to SRT subtitles via faster-whisper. Auto language detection + original-text alignment for subtitle correction.
SkillMIT★ 1Few starsNo key
SkillMITFew starsNo key
A powerful Model Context Protocol (MCP) server for YouTube video transcription and metadata extraction.
SkillMITFew starsNo key
GPU meeting transcription skill for Claude Code — 90x realtime on H100 using WhisperX
SkillMITFew starsNo key
Who stands behind it
