A study published in Nature Neuroscience on September 14, 2026, reports that signals from one cortical implant supported simultaneous decoding of attempted speech and upper-body gestures in two people with paralysis. Their decoded gestures animated personalized virtual avatars, while decoded speech appeared as text. This was a controlled research demonstration—not a product people can buy or a proven everyday communication system.
How the brain-controlled avatar system worked
The researchers recorded neural activity using a high-density electrocorticography (ECoG) implant. They first tested whether signals from a single cortical implant could decode isolated upper-limb and orofacial movements in three participants. They then tested parallel speech and gesture decoders with two participants, who attempted speech phrases, gestures, or both while controlling personalized full-body virtual avatars.
| # | Preview | Product | Price | |
|---|---|---|---|---|
| 1 |
|
Brain-Computer Interface Technologies: Accelerating Neuro-Technology for Human Benefit | $93.01 | Buy on Amazon |
| 2 |
|
Brain Computer Interface | $47.24 | Buy on Amazon |
| 3 |
|
Brain Computer Interface | $2.99 | Buy on Amazon |
| 4 |
|
Brain-Computer Interfacing: An Introduction | $44.99 | Buy on Amazon |
The interface translated the two kinds of output differently: decoded gestures moved the avatar, while decoded speech was displayed as text on screen. The team evaluated both a cued copy task and a task based on conversational prompts.
What “simultaneously” means here
The system was designed to decode attempted speech and gestures in parallel, allowing a participant to produce both kinds of intended output in the same interaction. It did not demonstrate ordinary spoken audio from the avatar: the speech output reported in the interface was text.
The Tool Desk
Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →#1 Best Overall
What the conversation-task results showed
Accuracy varied by participant and task. In the conversation paradigm, the study reported these individual results:
| Participant | Gesture decoding | Speech decoding | Reported chance levels |
|---|---|---|---|
| Bravo-6 | 85.0% average across five blocks (95% confidence interval: 70.0–100.0) | 75.0% average across five blocks (95% confidence interval: 55.0–90.0) | 9.1% for each decoder |
| Bravo-1r | 100.0% median across three conversational blocks | 100.0% median across three conversational blocks | 20.0% for gestures; 16.7% for speech |
These percentages describe two participants in experimental tasks; they are not estimates of how accurately the system would work for future users. The authors also report that training with isolated and simultaneous data improved performance across behavioral contexts.
Rank #2
What the avatar conversation did—and did not—demonstrate
The researchers described a virtual conversation in which a participant’s brain-controlled avatar interacted with a second avatar. An experimenter operated the second avatar using keyboard-entered speech and gesture commands. This was a qualitative demonstration in a research setting, not an unsupervised conversation service or evidence of independent everyday use.
Is this brain implant available to use?
No. The paper describes an experimental clinical research system, and the available study and institutional summary do not identify a consumer product that provides this capability. The authors frame the result as a step toward more natural communication for people with paralysis, rather than a ready-to-use device.
Rank #3
The institutional summary says testing with more participants and larger word and gesture sets is needed before practical use. The reported work establishes a proof of concept; it does not establish how well the approach would generalize beyond the two participants who used the parallel decoders.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.When the study was conducted
The trial began in November 2018. Data collection for this study ran from September 2022 through November 2025, and the paper was published on September 14, 2026. The publication date is therefore later than both the trial start and the data-collection period.
Quick Recap
Rank #4
Sources
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
