voice-ui

On-device Speech-to-Intent engine powered by deep learning

A programmable version of Neil Thapen's Pink Trombone

Application to communicate with SEPIA via browser, iOS and Android. Works as chat messenger with personal-assistant, ASR and TTS integration.

🤖 The Ultimate AI Form Filler. Automate complex web forms & PDFs with Voice, generic LLMs (Gemini/Phi-2), and Playwright. The best open-source autonomous form filling agent.

Open source image editor for windows 10. Can be controlled by voice commands and Cortana.

Voice I/O for LLM chat UIs: dictation, read-along and a voice-reactive aura, for any OpenAI-compatible speech engine.

On-device wake-phrase detection for Linux aarch64 — one glibc-2.17 .so behind Python (PyPI wheel), Node.js (npm), Go (go get), C/C++ (tarball + CMake), Rust. RTF 0.053 on Raspberry Pi Zero 2 W. Same runtime as voxrt-wake-word-{android,ios}.

On-device wake-phrase detection in the browser — WebAssembly + SIMD128, ~275 KB total (runtime + model), no server. Same runtime as voxrt-wake-word-{android,ios,linux}. Free demo tier of the VoxRT wake-word family.

On-device 14-way keyword spotting in the browser — WebAssembly + SIMD128, ~1.5 MB total (runtime + model), no server. Same runtime as voxrt-kws-{linux,android,ios}.

Always-on wake-phrase detection for iOS on the VoxRT custom on-device inference runtime — Swift Package, 16 kHz mono PCM in, threshold-crossing events out. Custom phrases at voxrt.com.

Always-on wake-phrase detection for Android on the VoxRT custom on-device inference runtime — Kotlin library, 16 kHz mono PCM in, threshold-crossing events out. Custom phrases at voxrt.com.

14-way keyword-spotting model weights (.vxrt v2, AES-256-GCM encrypted) for the VoxRT on-device runtime. Streaming Conformer-Medium (636 K params, 1.28 MB). Paired with voxrt-kws-{linux,browser}.

Wake-phrase model weights (.vxrt, ~100 KB, AES-GCM encrypted) for the VoxRT custom on-device inference runtime. Paired with voxrt-wake-word-{android,ios,linux}. Custom phrases at voxrt.com.

Local-first VAD, barge-in, and turn-taking primitives for interruptible voice agents.

A voice-controlled spin on "Who Wants to Be a Millionaire?", made with Unity

The Estonia One Hundred Alexa Skill

A Plug & Play AI Voice Agent Powered By ChatGPT. Intelligent in-App context-aware Agent with Voice UI Controller. One VoiceBot for all your Apps & Websites!

AI-powered web builder — generate UI via voice commands, clone any website from a screenshot, and collaborate in real-time with Liveblocks

🎙️ Lightweight offline Python TTS engine. Thread-safe, CLI-ready, and modular. Speak text locally or save to disk with pyttsx3.

AI-powered productivity app that helps overwhelmed users turn spoken thoughts into prioritized, actionable tasks.