aarushyadav

Amazing! Supports just English for now, but we will keep pushing out other languages as software updates after shipping, with Spanish as the second planned language.

That's fair, will rethink!

Tbh we haven't tried internal speech on outsiders yet, just the two of us and one of our employees. We were able to solve it on that small set, so it's technically solvable with enough user specific internal speech personalization data. But the amount of time it took us to learn the behavior comfortably is a bit too high for us to focus on it as a key feature we have from the beginning. In a few months though we will start collecting larger scale data on internal speech as well.

Additionally, we found that you can mouth words discreetly enough / with no exaggerated movements, such that people sitting around you would likely not notice unless they were staring at you, which seems to be good enough, as a start at least.

We did consider that, but it's a bit hard to fit all the electronics well and distribute the antennas optimally and keep that consistent across people and glasses. Best to have a predictable deice we can engineer to the needs of this application!

Yep. You can either just dictate silently and we can transcribe, or another feature we will likely push out as a software update is where you can speak out loud and the RF signal is used to fully and almost perfectly denoise the audio of you speaking.

Fair enough! We take data security and privacy very seriously and have built many safeguards to prevent even us from accessing the raw data in the cloud. At some point in the future we hope to launch local inference models too!

Glasses are a great way to provide output back, via an AR display, and also offer more real estate to fit the electronics and antennas in.

Yes, this is the unoptimized speed while we are in development. We are working hard to make it much faster for production!

When we launch, no, it will be cloud inference, but will be processed with encryption in hardware isolation and only retained and used for anonymized training with your consent. At some point in the future we may make models available for local inference though.

English only right now, plan to add support for others after shipping

this should be fixed now!

Not well enough! You can get to 15-20%ish WER but going beyond that doesn't seem feasible with the info available from a camera, even with a great language model

The glasses will have open ear speakers similar to meta glasses! We plan to make our own agent harness and connect it native with the glasses. I have meta glasses but rarely use the AI since it's weird to talk out loud to ask it things when I'm out. This is how we want to solve it

Yep, we have been quite set on nose pads to keep them comfortable. I will keep you updated with the designs!

The decoding is done via a companion app on your laptop or phone in the cloud, but end to end latency is still quite fast, under 500ms usually.

To begin with we don't plan to have a wake word, but rather a trigger key on your connected device that you're entering text into (pressing Alt for example), similar to Wispr Flow. We're doing some R&D into the silent speech equivalent of voice activity detection, so we have a low power basic RF detection always-on, not enough to decode speech from but enough to detect rough movement, and when it detects speech-like activity beginning to start we can trigger full sensing within tens of ms. This would likely ship as a software update a few months after shipping, though.

The voice change demo is something I've thought about actually, but we never got around to doing. Might film it soon :)

Not sure, but definitely sounds interesting! I do know there was one company trying to use mmWave RF to track patient vitals like breathing patterns and heart rate without having anything hooked up to / touching them

From my understanding decoding via ear deformation requires the mouthing to be quite exaggerated. I am also looking forward to Apple launching it soon though, hopefully it gets more people excited and aware about the category at least

It's not :)

Yup, Q.ai is different tech and we have our IP :)

They use speckle patterns of a laser shone onto the skin, which is sensitive down to tens of nanometers. Pretty cool tech

Yup those are pretty cool too! How do you feel about quiet whispering vs completely silent? Genuinely curious we haven't asked too many people

Yes, it requires internet access

Of course! Privacy is important!

No, the RF is very low power and can safely be active on your face for long periods. We've done a lot of investigation and verification with safety. While doing R&D the first 2 months we collected hundreds of hours of data on ourselves with various configurations, so we made sure it was safe before :)

Also, the RF transmission only activates when you're actively dictating.

Fair feedback, will take into account. Looking to change up the site quite a bit soon!

Yep, I agree. Noise cancellation is a feature we want to release at some point in the future. Using the RF to denoise a very noisy audio signal which has you speaking in it. And we'll release an SDK as well a few months after shipping to build stuff on top of it!

No throat mic, the first image uses EMG (muscle electrical signal) sensors. A throat mic only works if you're still actually whispering (not fully silent) and is also a weird form factor for a consumer device, which is why we didn't go with it!

Looking into it

There's subtle changes in internal speech muscles as well often for those kinds of movements, and where it does seem ambiguous language context is usually enough to distinguish

Most people type at 40-50 WPM. Developers can often type at 70-100 WPM. Meanwhile, most people can talk at 120-200 WPM. Beyond just speed, we've found with many people that talking things out tends to flow more naturally, since it's often a lower friction action so people don't "sanitize" the text in their head before outputting it. Leads to better prompts quite often :)

That makes sense. We will implement that!

Yup that makes sense. Thanks for the feedback, we'll make some changes shortly!