←News detail

IT Home · Artificial IntelligenceUpdated Oct 30 14:58

Neuralink Publishes Early VOICE Project Data: ALS Patient Reaches 75 Words Per Minute Output in First Week After Implant

AI summary

Neuralink released a blog post on October 28, publicly disclosing the early feasibility study of its speech restoration project VOICE. One participant with ALS reached an output rate of 75 words per minute in the first week of use, with a word error rate of 5.8% on a large vocabulary of 125,000 words. The study's lead investigator, Dr. Nader Pouratian, has presented the relevant data at the 2026 NEALS annual meeting. The study plans to enroll approximately 6 participants who have lost the ability to communicate due to ALS, spinal cord injury, or stroke, and its primary endpoint is device- or procedure-related adverse events within 12 months after implantation. Neuralink has not yet published a complete peer-reviewed paper; the figures come from a single participant, and the company has not explained the types of test tasks, the separate performance of text versus speech output, or long-term effects.

Why read this

AI score 62

Neuralink published output data showing 75 words per minute in the first week for an ALS patient, while also clarifying the sample size and the boundaries of the non-peer-reviewed work.

Topics

Tags

Body · AI translation

Neuralink, Musk's brain-computer company, achieves new breakthrough: ALS patient reaches 75 words per minute output in first week of implant, approaching normal conversation

2026-10-30 11:07 IT Home - Guyuan

IT Home, October 30 news: Neuralink, the brain-computer interface company owned by the world's richest person Elon Musk, published a blog post on October 28, disclosing the early feasibility study of its speech restoration project VOICE, enabling a participant with amyotrophic lateral sclerosis (ALS, commonly known as "Lou Gehrig's disease") to convert brain signals into text and speech output at a speed approaching conversation.

Citing a tweet, IT Home reports that one participant reached an output speed of 75 words per minute (WPM) in the first week of use; with a large vocabulary of 125,000 words, the word error rate (WER) was 5.8%, meaning roughly 1 error in every 17 words.

The company said that the study's principal investigator, Dr. Nader Pouratian, has presented the relevant data at the 2026 NEALS annual meeting; the study plans to enroll about 6 participants who have lost communication abilities due to ALS, spinal cord injury, stroke, or other causes, with the primary endpoint being device- or procedure-related adverse events within 12 months after implantation, and speech performance as a secondary endpoint.

For ALS patients, the disease progressively impairs communication abilities such as speaking and typing. If a brain-computer interface can reliably decode "what one wants to say" into text and further synthesize speech, it could significantly lower the barrier to communicating with others.

The 75 words-per-minute speed announced this time has entered the range that can support relatively fluent conversation; the 5.8% error rate also means the system can still preserve most of the meaning with a relatively large vocabulary.

Neuralink currently discloses results through social platforms and academic conferences and has not yet published a complete peer-reviewed paper; the figures come from a single participant, and the company has not explained the type of test task, the separate performance of text and speech output, data stability, or long-term effects.

Reference

Proceedings of the 25th Annual Meeting of the Northeast ALS Consortium

Advertising statement: External redirect links contained in the article (including but not limited to hyperlinks, QR codes, passwords, and other forms) are used to convey more information and save selection time; the results are for reference only, and all articles on IT Home containing external links include this statement.

Source

IT Home · Artificial Intelligence