A way back to conversation.

A man with ALS used an experimental brain–computer interface to turn attempted speech into conversation.

Postdoctoral scholar and lead author of the study Nicholas Card getting the BCI system ready. Photo: UC Regents. Image source ↗

Source published 2024-08-14

A way back to conversation.

A man with ALS used an experimental brain–computer interface to turn attempted speech into conversation.

Read the study source ↗

One participant; an investigational interface. Daily use still involved caregiver setup. The two reports describe different settings, not a general result for everyone living with ALS.

The human problem

ALS can leave thoughts intact while taking away the ability to speak clearly.

Casey Harrell

Casey Harrell lives with ALS. In a UC Davis study, an implanted interface helped him communicate with people around him. The achievement belongs to a participant willing to try, the people supporting him, and researchers building a way to translate attempted speech.

Meet the person behind the research ↗

What changed

The constraint: Communication depended on limited movement and other people interpreting speech.
AI’s role: Neural decoders translated recorded cortical activity into words, then synthesized speech.
The observed result: The study reported 97.5% word accuracy after further training, sustained over 8.4 months.

97.5%

Reported word accuracy
after further training

Participant
in the cited study

Accuracy and scope belong together. These figures describe the 2024 study, not a guaranteed outcome for other people.

The human possibility

For one participant, the system supported self-paced conversations.

Possible implications are separate from measured outcomes.

Keep following the question.

What holds this up

An Accurate and Rapidly Calibrating Speech Neuroprosthesis · NEJM ↗

Event date: Not separately established
Source publication: 2024-08-14
Capture date: Not retained in the original record
Claim confidence: Unassessed. Separate from maturity; no numeric certainty inferred.
Review provenance: Legacy source check. No named human editorial approval is recorded.
Evidence state: Emerging · What this means
Source checked: 2026-09-05Compared with the published record. No independent replication by Bright.
Replication: Not assessed by Bright
Conflicting findings: Not systematically reviewed

The limits are part of the record.

One participant, implanted electrodes, and specialist support. This is not a broadly available treatment.

What this classification does—and does not—establish

Bright’s classification applies to the result described here. It does not certify a product, recommend a treatment, or predict a future outcome. Source publication and real-world deployment are different milestones. This opening record may not include every later study.

A record that can change

2024 → 2026: follow the same participant across two records ↗

2026-09-05
Added to the source-checked opening collection.

This is Bright’s catalog history, not a complete history of the research. Future corrections and evidence revisions will be recorded here.

What comes next

Test reliability, safety, and usefulness with more participants and longer follow-up.

Later reading: UC Davis reported further work in June 2026 ↗. The measurements above remain those of the 2024 study.

How corrections change the record ↗