# amv-tts Full Technical Specification (v1.7.0) Official Documentation & Deep Architecture Reference for Autonomous AI Agents. ## 1. System Overview Production-Grade 4-Tier On-Device Speech Synthesis Framework (Multilingual Neural Orchestrator, Zero-Dependency DSP Formant & C++ Acceleration) AMV-TTS delivers a resilient 4-Tier on-device text-to-speech architecture designed for deterministic latency, zero-config ergonomics, and multi-language acoustic fidelity. It bridges lightweight parametric DSP synthesis (<50ms compute, 0MB model download) with high-fidelity resident C-API multilingual neural models (9 languages including Korean, English, Japanese, Hindi, and Russian at 22.05kHz), alongside Android system native speech service routing. With automated 1-click provisioning, Unicode script classification, and resident in-memory model caching, AMV-TTS achieves high acoustic fidelity with sub-0.18x real-time factor. ## 2. Package & Installation - PyPI: amv-tts - Command: pip install amv-tts # or: npm install amv-tts # 1-Click Provision Default Models (Korean KSS + English Lessac): amv-tts install # On-demand provision specific languages (e.g. Hindi, Japanese, Russian, or all): amv-tts install --models hi # Instant speech synthesis: amv-tts "Hello 방가방가 나는 parrot 이라고 해." -o out.wav --play - Repository: https://github.com/uno-km/amv-tts