# AMV-STT Full Technical Specification (v2.1.0) Official Documentation & Deep Architecture Reference for Autonomous AI Agents. ## 1. System Overview Unified On-Device Speech-to-Text & Neural Multi-Speaker Diarization (PyAnnote 3.0 + CAM++ 192d + TS-VAD Overlap Resolver) Integrates Whisper.cpp (Native Vulkan GPU / NEON CPU) and Sherpa-ONNX with PyAnnote 3.0 neural segmentation, 3D-Speaker CAM++ 192-dim embeddings, and TS-VAD overlapped speech resolution with zero cloud egress. ## 2. Package & Installation - PyPI: amv-stt - Command: pip install --upgrade amv-stt && amv-stt install # or Node.js: npm install -g amv-stt && amv-stt install - Repository: https://github.com/uno-km/amv-stt