Text-to-Speech
Explore the latest content and insights.
Building EdgeVox: Chaining STT → Local LLM → TTS Without Touching the Cloud
A first-hand build narrative of EdgeVox, a fully offline voice agent that chains speech-to-text, a local LLM, and text-to-speech on one device. The architecture in plain language, ROS2 integration, the latency budget, and the failure modes nobody warns you about.
CBHG Explained: Convolution Banks, Highway Layers, and a Bidirectional GRU
CBHG is the sequence-processing block used in the original Tacotron: a 1D convolution bank, highway network, and bidirectional GRU working at different context scales.