[ STACK LIBRARY ]

VoxRT

VoxRT

Visit website

Speech-to-Text

ABOUT

On-device voice AI SDK for wake words, voice commands, and streaming speech-to-text that never sends audio to the cloud.

VoxRT builds on-device voice AI engines, including custom wake words, voice activity detection, and streaming speech-to-text, on a CPU inference runtime written in Rust. Its production binaries stay under one megabyte, audio never leaves the user's device, and models work offline by default. Published models are free for commercial use, with custom models tuned per customer. The company ships SDKs for mobile, Linux, Python, Node.js, Go, and C or C++, with desktop, web, and microcontroller support planned.

STACK COVERAGE

Speech-to-Text

Wake word detection, Voice activity detection, On-device speech-to-intent

DETAILS

FOUNDED

2026

LANGUAGES

English

DEPLOYMENT

On-device SDK

PRICING MODEL

Freemium, Enterprise/Custom

Is this your company? To claim this listing or update its details, contact us at sunil@uniocommunity.com

UNIOVOICE AI STACK LIBRARY
VoxRT logo
Trusted by Unio

VoxRT

Speech-to-Text

On-device voice AI SDK for wake words, voice commands, and streaming speech-to-text that never sends audio to the cloud.

Wakeworddetection,Voiceactivitydetection,On-devicespeech-to-intent
Layer
Speech-to-Text
Market
Global
Founded
2026
Deployment
On-device SDK
Pricing
Freemium, Enterprise/Custom
Languages
English
Listed on the Unio Voice AI Stack Library

More in this layer

var(--variable-H7lUBNgYB)

SpeechRouter

Speech-to-Text

Unified speech-to-text gateway that routes one API across 17-plus providers with mid-stream failover.

var(--variable-H7lUBNgYB)

3Play Media

Speech-to-Text

Video accessibility and localization platform that combines AI with human review for captions, audio description, subtitles and dubbing.

var(--variable-H7lUBNgYB)

AI-coustics

Speech-to-Text

Real-time speech enhancement that cleans audio so voice AI transcribes and responds reliably.