Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

VOX: Voice Operator eXperience A stethoscope for your voice: works at low volume and in loud environments. Across all your devices and agents.

50,489 Aufrufe • vor 1 Monat •via X (Twitter)

19 Kommentare

Profilbild von Augmental
Augmentalvor 1 Monat

Voice travels through your body and vibrates your skin. The skin acts like a speaker diaphragm, displacing the air at its surface. That's the air VOX listens to, instead of pointing a mic at your face the way an earbud does.

Profilbild von Augmental
Augmentalvor 1 Monat

It's a prototype. It doesn't work perfectly everywhere yet. Not silent speech either: you still speak, and someone close might hear. But it already beats AirPods on low-volume dictation, unlocking workflows an ordinary mic can't.

Profilbild von Augmental
Augmentalvor 1 Monat

No wake word, no continuous listening. Capture starts when you press and stops when you press again.

Profilbild von Augmental
Augmentalvor 1 Monat

Four buttons: one to dictate, one for power and switching devices, and two you map to whatever you want. Single and multi-press. Enter, Spotlight, cmd+tab, whatever you want, without looking or reaching for the keyboard. Pace around instead of sitting at a desk. Untether yourself.

Profilbild von Augmental
Augmentalvor 1 Monat

11 grams. 35 x 37 x 12 mm. USB-C. Light enough that you forget it's on, so it's there whenever you need it.

Profilbild von Augmental
Augmentalvor 1 Monat

We follow universal design: build for the most constrained, and you get better interfaces for everyone. Current MouthPad users live with a range of speech differences, from weak voices to limited breath support. VOX improves access to voice input, and it turns out most people want to talk to their computer without the room hearing it.

Profilbild von Augmental
Augmentalvor 1 Monat

$200, refundable any time before it ships. Q4 2026, US only for now. Everything you pay goes toward MouthPad units for people who need one and can't afford it.

Profilbild von Lev Chizhov
Lev Chizhovvor 1 Monat

It works great, based on a bit of playing with it!

Profilbild von Chris Samra
Chris Samravor 1 Monat

Is that Apple’s native keyboard on the phone? If this is done on iOS through accessibility and not having to use a 3rd party keyboard that’s really sick.

Profilbild von Ricky Rosa
Ricky Rosavor 1 Monat

Oasis + Vox is gonna change the voice game

Profilbild von tr
trvor 1 Monat

Invisible interfaces lets gooo

Profilbild von superwhisper
superwhispervor 1 Monat

ok fine no more prompt masks...

Profilbild von Carlos Galarza
Carlos Galarzavor 1 Monat

Love this!! If I order, when would I receive it? are you only taking online orders and can I walk into your office and buy one?

Profilbild von Ricky Rosa
Ricky Rosavor 1 Monat

Lets gooo

Profilbild von Patricio Escobar
Patricio Escobarvor 1 Monat

How much for the Revlon hair blower? ps. VOX seems awesome, my Mac microphone always mis-hears me :{ and I have to "shout".

Profilbild von Alex Debelov 🚀
Alex Debelov 🚀vor 1 Monat

Can't wait to try this!!!

Profilbild von Evelyn
Evelynvor 1 Monat

Reliable voice interaction is the missing piece for AI agents. Excited to see solutions that work seamlessly in real-world environments. 🎙️🚀 A voice interface that performs well even in noisy environments could be a game changer for AI assistants. Great work! 👏 Natural, hands-free interaction is the future. Looking forward to seeing how VOX enhances AI agent experiences across devices. 🔥 Voice AI keeps getting better. Robust performance across different environments is exactly what users need for everyday adoption. 💡

Profilbild von Mikel Gonzalez
Mikel Gonzalezvor 1 Monat

Awesome! Ordered!

Profilbild von MR ANDERSON
MR ANDERSONvor 1 Monat

Really impressed by the focus on reliable voice interaction. A voice interface that works across noisy environments and seamlessly connects with AI agents could make hands-free AI far more practical. 🎙️🤖

Ähnliche Videos

Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with LiveKit and RealAvatar, and taught by dsa (Co-founder & CEO of LiveKit), Shayne (Developer Advocate, LiveKit), and Nedelina Teneva (Head of AI at RealAvatar, an AI Fund portfolio company). Voice agents combine speech and reasoning capabilities to enable real-time conversations. They're already being used to support customer service, to improve accessibility in healthcare, for entertainment applications, and for talk therapy. In this course, you’ll learn to build voice agents that listen, reason, and respond naturally. You’ll follow the architecture used to create the "AI Andrew" Avatar, a collaborative project between and RealAvatar that responds to users in what sounds like my voice. You’ll build a voice agent from scratch and deploy it to the cloud, enabling support for many simultaneous users. What you’ll learn: - Understand the fundamentals of voice agents, including key components like speech-to-text (STT), text-to-speech (TTS), and LLMs, and how latency is introduced at each layer. - Explore voice agent architectures and the trade-offs between modular pipelines and speech-to-speech APIs. - Explore how platforms like LiveKit mitigate latency issues with optimized networking infrastructure and low-latency communication protocols. - Learn how to connect client devices to voice agents using WebRTC—and why it outperforms HTTP and WebSocket for low-latency audio streaming. - Incorporate voice activity detection (VAD), end-of-turn detection, and context management to detect turns, handle interruptions, and manage conversational flow. - Understand the trade-offs between latency, quality, and cost in an example in which you build a voice agent and change its voice. - Equip your agent with metrics to measure latency at each stage of the voice pipeline and learn the key levers you can pull to make your agent faster and more responsive. The voice agents built in this course also incorporate voice technology from , a supporting contributor to the project. By the end of this course, you'll have learned the components of an AI voice agent pipeline, combined them into a system with low-latency communication, and deployed them on cloud infrastructure so it scales to many users. I’m looking forward to seeing what voice agents you build from this course! Please sign up here:

Andrew Ng

87,810 Aufrufe • vor 1 Jahr