Our new preprint describes a multimodal intracortical brain-computer interface that a man with ALS has used at home, independently, almost every day for >19 months. It decodes both speech and cursor control to enable him to communicate and use his computer. Here’s a quick tour👇

RT @WillettNeuro: Build the next generation of communication BCIs with us—now hiring a new postdoc! Application here: .

Thanks to my coauthors and mentors for making this work possible! @SergeyStavisky @DrDavidBrandman @neuroleigh @Maitreyee_W @ca_rrina Xianda, Tyler, Elena, Hamza, Zach.

This work demonstrates that intracortical BCIs can be used independently and productively in a real-world setting, reliably supporting both communication and digital access over nearly two years of use. Read the preprint for more details:

Speech and cursor decoding performance remained accurate for more than 19 months post-implant, enabled by stable and high-quality intracortical neural signals.

With brain-to-text as keyboard input and cursor + click as mouse input, he:. 💬 Texts & emails. 🌐 Browses the web. 🛍️ Stays on top of finances and shopping. 🧑‍💻 Works full-time.He told us: “I am basically using my computer in the same way as I was doing before the disease.”

Cursor movement and click decoders enabled him to navigate the BCI system user interface and control his own personal computer. Just 10 minutes of explicit calibration a day gives him reliable all-day cursor & click control.

Brain-to-text decoding enabled every-day conversation:.- 183,060 sentences ➡️ 1.96 M words.- Avg 56 WPM.- 92% of sentences self-rated as mostly correct or better.- >99% word accuracy in Copy Task benchmark sessions >600 days post-implant (125k-word vocab)

Participant T15 has four 64-electrode Utah arrays in his speech-motor cortex. His care partners plug in and turn on the system, and then he can reliably use the BCI all day long with little-to-no explicit calibration. He’s already used it independently for over 3,800 hours!

I'm really excited to receive the BWF CASI! This award will help support me as I continue to develop BCIs that restore communication. Congratulations to the other recipients as well!.

RT @UCDneurosurgery: Postdoctoral fellow @NS_Card is a recipient of the @BWFUND 2025 Career Awards at the Scientific Interface (CASI)! This….

As the competition progresses, we'll continue to add baseline results using some of the lessons learned from the prior Brain-to-Text '24 competition: Good luck!.

You can learn more about the dataset at the competition link, above! We also provide a baseline algorithm and examples of how to load the data, train a model, evaluate the model, and generate a submission file on our GitHub repo:

We're excited to announce the Brain-to-Text '25 competition, with a new intracortical speech neuroscience dataset and $9,000 in prizes generously provided by @BlackrockNeuro_!. Can you do better than us at decoding speech-related neural activity into text?.

RT @Maitreyee_W: Our brain-to-voice synthesis brain-computer interface paper was published in @Nature today! This neuroprosthesis synthesiz….

Great next-generation speech BCI work led by our very own @Maitreyee_W !.

RT @SergeyStavisky: Another preprint 🧵: our first foray into 𝐡𝐲𝐛𝐫𝐢𝐝 𝐜𝐨𝐠𝐧𝐢𝐭𝐢𝐯𝐞 + 𝐦𝐨𝐭𝐨𝐫 𝐬𝐩𝐞𝐞𝐜𝐡 𝐛𝐫𝐚𝐢𝐧-𝐜𝐨𝐦𝐩𝐮𝐭𝐞𝐫 𝐢𝐧𝐭𝐞𝐫𝐟𝐚𝐜𝐞𝐬. Ever wished your ph….

RT @biorxiv_neursci: Error encoding in human speech motor cortex #biorxiv_neursci.

RT @SergeyStavisky: 📢 Heads-up to the neuro-ML/BCI community that we'll launch the Brain-to-Text '25 competition in ~a month, and it'll run….

RT @SergeyStavisky: Now published in the Journal of Neural Engineering!.