VoxRT

About

VoxRT is an on-device voice AI runtime built in Rust from scratch. No ONNX, no TFLite. A NEON-tuned engine for ARMv8 and WASM SIMD128 that runs speech models locally on mobile, single-board computers, and in the browser. The stack: - Wake-word "Hey Assistant": ~100 KB, 5.3% RTF on a $15 Raspberry Pi Zero 2 W - Silero VAD (MIT) on our runtime: 3.05% RTF on a 2020 mid-range Android - Streaming ASR (NeMo FastConformer): real-time on mobile, WER 3.267% LibriSpeech - 14-command KWS: 16% RTF on Snapdragon 662, 0.97% in Chrome WASM SDKs are Apache-2.0 wrappers around a proprietary runtime. Custom phrases and vocabularies are a paid tier. Try in the browser: - https://voxrt.com/wake-word-demo - https://voxrt.com/asr-demo - https://voxrt.com/asr-demovoxrt.com/kws-demo

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Forums

How small can a wake-word be? 100 KB, launching Wednesday

Team at VoxRT here.

Next Wednesday (Sept 2) we go live on Product Hunt. Follow @voxrt or hit the Notify me button above so you don't miss it.

2d ago

Hi from the VoxRT team (on-device voice AI)

Team at VoxRT here. We've spent the last year building a Rust runtime for on-device voice AI (wake-word, VAD, streaming ASR, voice commands) that runs on iOS, Android, and Linux. Wake-word and voice commands also run in the browser via WASM. No cloud, no per-minute fees, no audio leaving the device.
SDKs are already shipping on github.com/VoxRT (JitPack, SPM, PyPI, npm, Go), and you can try the wake-word and voice commands demos in your browser.
Happy to answer questions about on-device voice AI, benchmarks, or licensing tradeoffs. Say hi if you're in the same space.

View more