Explore
MCP servers and skills: search, filter by where they run, and compare.
genpark-audio-packet-jitter-resilience-buffer-skillAlpha-Park
HostedPacket ordering simulation and inter-arrival jitter telemetry.
MCPLink only★ 7
MCP servers and skills: search, filter by where they run, and compare.
Packet ordering simulation and inter-arrival jitter telemetry.
MCPLink only★ 7
Energy and transcript heuristics for voice turn endpoint detection.
MCPLink only★ 7
Adaptive WebRTC audio packet jitter buffer and packet loss concealment (PLC) engine maintaining smooth voice playout over volatile network streams.
MCPLink only★ 7
Real-time acoustic VAD & semantic turn-completion endpoint detector distinguishing mid-sentence hesitation pauses from finished speech turns.
MCPLink only★ 7
Working towards an MCP setup that allows humans to format audio with an agent in the loop. Useful for repetitive audio formatting tasks where the content is well defined.
PythonMIT★ 1Few starsNo key
🎙️ MCP Speech-to-Text Server with Enhanced Cantonese Support | Offline Vosk + Online Google Cloud | Auto-detection for zh-HK | n8n workflows | Hong Kong optimized 🇭🇰
PythonMIT★ 2Few starsNo key
Declarative AI pipelines in one YAML file. Tokens, audio chunks, and video frames flow between isolated components. Compose 100+ components for models, agents, speech, vision, and live broadcast. Run
PythonMIT★ 120No key
VidXP (Video eXPlain) - Video Indexing Engine. Search in videos in natural language. 👀 Connect your Hermes / Claude / OpenClaw agents, allow them to understand videos with low token cost.
PythonMIT★ 59No key
PythonApache-2.0★ 25No key
Turn videos and courses into evidence-grounded Agent Skills for Claude Code and Codex.
SkillMIT★ 39No key
Recordings in. Agent-ready evidence out. Local-first MCP for transcripts, keyframes, OCR, speakers, and wall-clock evidence.
PythonMIT★ 32No key
An MCP Server for audio transcription using OpenAI
PythonMIT★ 60No key
Small server that exposes an Ollama compatible interface to MLX
PythonMIT★ 6No key
Let AI watch videos: local files or YouTube/Bilibili URLs -> timestamped transcript + keyframes + contact sheets. Offline, no API key. MCP server + CLI + agent skill.
PythonMIT★ 11No 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
TTS toolkit built on Kokoro-82M with librosa audio enhancement, MCP server for Claude/Cursor, CLI & Python API. Free & open-source for YouTube creators.
PythonApache-2.0★ 15No key
PythonMIT★ 1Few starsNo key
Vocal Helper is an async producer/consumer pipeline turning audio into diarized, transcribed utterances
SkillBSD-3-Clause★ 1Few starsNo key
CuePrecise — Analyze an hour-long YouTube video sentence by sentence in three minutes, and extract the information you need from the screen. Open-source MCP server for AI clients.
PythonMIT★ 2Few starsNo key
Drop raw clips in a folder, get silence-cut, subtitled video. Subtitles in 90+ languages (auto-detected), filler-word removal, runs locally. Claude Code plugin + CLI.
SkillMIT★ 1Few starsNo key
PythonMIT★ 1Few starsNo key
Generate long-form multi-speaker audio from YAML using Google Cloud high quality TTS models (incl. EU ML Processing!). Python library with CLI, FastMCP, and ADK adapters; async jobs so agents don’t bl
PythonApache-2.0Few starsNo key
Who stands behind it
