1. Voice activity detection To remove the need for pressing a button to start and stop recording of speech intention, we created a system for automatically detecting when a user is and isn’t trying to speak. This is a big step towards making communication for those with speech impairment... completely hands-free.show more

Our engineers recently visited one of our speech restoration study participants for a 72-hour hackathon. The goal: rapidly prototype as many features as possible to enhance the experience of using Neuralink to communicate with thought. Here are some of the things we built 🧵

2. Real-time visualizations One of the technical challenges with brain-computer interfaces (BCIs) is figuring out what intended or imagined actions produce the strongest neural activity to improve decoding model performance. We configured a variety of visualizations designed to give our participants real-time feedback on the intensity and distribution of signals detected by our implant.

3. Computer use agent We prototyped a feature to enable users to trigger a Grok agent by thinking of saying “Hey Neuralink” along with a desired task. This is an early illustration of how increasing the bandwidth of communication between the brain and computers could help close the gap between thought and action.

4. Mobile app for speech Over the last few months, we’ve put significant effort into building Bloom: a mobile app to make speech BCI more accessible. The hackathon gave us an opportunity to see the real-world user experience and identify ways it could be improved.

5. Phone call integration Voice calls are an essential part of daily life. We integrated Bloom with iPhone calling so BCI speech is injected directly into the call’s mic stream, giving the other person clear, consistent audio. We also tested optional greetings to play at the beginning of calls (e.g., “this call is from someone using an assistive communication device”).

The hackathon is over, but we’re just getting started. The list of things we want to improve and build continues to grow. We need exceptional engineers across machine learning, software, and many other disciplines to help shape this technology that will transform human interaction and advance human agency in an era of AI. If this resonates, visit

If you’re interested in learning more about the hackathon experience, check out our blog:

Neuralink devices are investigational and have not been approved by the FDA or other regulatory authorities. These videos feature voluntary clinical trial participants sharing their personal experiences, which may not reflect all participants or future outcomes.

Amazing! I don't know why more media outlets are not talking about this.

This is beautiful. Watching thought turn into voice, hands-free, for someone who lost that — it feels like giving a person their presence back.♥️

World class engineers dropping ‘we vibecoded’ lol amazing

I imagine it’s possible to accidentally have the machine dictate your thoughts that you meant to NOT say out loud.

Automatic detection of speech intent is a big step. Brain tumor patients with language deficits could one day benefit from the same approach. Excited to see where this goes.

“Vibe coded quickly” wow, what a time to be alive.

Amazing advancements in how to improve the quality of life to so many patients. Communication is so critical to have and frustrating to lose.

God bless neuralink engineers.

Excelente

@grok can this feature be used by non verbal Autistic children

Oh God. Imagine you're thinking something bad about your wife and your phone just starts saying it out loud!

I need to study, thank you. ✍️

🫶🏻

Can you hook it up to enemy spies and read their minds

This is the type of engineering that makes me emotional. Great work Neuralink team!

@elonmusk you are one of the greatest gift for humanity. Watching this made me so emotional.♥️🙏

Can you open source this I feel like there’s so many devs who would like to create apps to help, I think creating an app with an interface to allow neuralink users create their own experimental apps would be amazing

too much noise, why are you processing data in 2D. you are receiving 3D data yet you flattening it and then processing it. you can get much better results and faster processing time you you filter out the noise by cutting out the noise, lower planes. cut noise then flatten.

right on

Sooner than we thought.

"Trust me Bro".

What if a neuralink user is in bed with their partner and says aloud, "choke me", and the fucking AI starts answering and ruins the vibe?

Maravilhoso!

کاش برای حرکت کردن هم میشد کاری کرد . اگر برای فلج های مغزی راهی باشه خیلی از مردم نجات پیدا می‌کنند .