Optimized ESP32-S3/P4 fully offline speech to text and text to speech system for Micropython and AtomVM, featuring a finetuned STT model for noisy environments, plus a data generation/field capture/model finetuning framework. Includes high performance 4/8bit int kernels for Xtensa/RiscV PIE vector units
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
Yo is a compie-time grammar compiler (Nix) and a runtime interpretor (Rust). In simple terms it's a deterministic natural-language command engine with an offline voice interface.
Run a <400ms latency Voice Agent on just 4GB VRAM. Fully offline, no API keys required. Optimized for GTX 1650 and edge robotics with zero-copy inference. (Apache 2.0)
Offline wake word & keyword spotting engine. One ONNX model detects multiple keywords. ONNX/TFLite, model <130KB, inference <10ms. Runs on Android, ESP32, Linux, Web, and Home Assistant (Wyoming protocol server + HA add-on). No cloud, no data usage.
