How close are we to giving speech back through a brain implant?Can an implant turn thoughts back into speech?
or, simply: Can an implant turn thoughts back into speech?or, precisely: How close are we to giving speech back through a brain implant?
Implanted electrodes can already turn neural activity into words on a screen; the open questions are speed, vocabulary, and whether it lasts for years.Electrodes read the brain's signals for speech. The race is to make them fast, accurate, and durable enough for daily life.
Wireless speech trial implants first - Connect-One implanted its first participant with a fully internal 421-electrode BCI designed to test text and synthesized speech. Next up - Two-person safety endpoint scheduled (expected May 2027).
State of playWhere speech bci stands right now
The current stage, the honest metric, and the single threshold that gates the next stage. Each threshold is a falsifiable claim with a named next test.How far up the ladder we've climbed, the honest verdict, and the one thing blocking the next step.
Electrodes read the brain's signals for speech. The race is to make them fast, accurate, and durable enough for daily life.Implanted electrodes can already turn neural activity into words on a screen; the open questions are speed, vocabulary, and whether it lasts for years.
Restore a natural voiceReal-time expressive voice Next test: Achieve under-10% listener WER on unseen spontaneous sentences with independently controlled pitch and emphasis.
The thresholds that gate the next stageWhat has to happen next
Each threshold is a falsifiable claim with a named next test; the gap chart shows how far today's metric sits from the goal.Each row is one thing that has to be proven — and how far today's number is from the target.
The record behind the verdict
Major events set large; context events set small but never hidden. Everything below the TODAY rule is a schedule, not a result.
The Direct-Link Hypothesis
The Direct-Link Hypothesis begins with direct brain-computer link proposed. The result established the next question for the field.
Single Channels Move Cursors
Single Channels Move Cursors moved the field from locked-in patient controls switch to braingate proves multidimensional control. The results narrowed the next question without closing it.
Motor Intent Becomes Language
Motor Intent Becomes Language moved the field from implant drives vowel synthesizer to cursor typing accelerates. The results narrowed the next question without closing it.
Neural Decoders Learn Speech
Neural Decoders Learn Speech moved the field from cortical activity synthesizes sentences to handwriting bypass reaches phone speed. The results narrowed the next question without closing it.
Records Confront Daily Life
Records Confront Daily Life moved the field from percutaneous risks stay visible to six-year follow-up scheduled. The results narrowed the next question without closing it.
Events outside the declared eras
Events outside the declared eras begins with ten-year wireless durability target. The result established the next question for the field.
Why the meters read the way they do
The learning curves and comparisons that justify each threshold's percentage. Every series is measured, with the source event linked in the timeline above.
Read the evidence more closely
Definitions, system boundaries and experimental caveats behind the headline record.
01Online bilingual decoding was windowed
The bilingual system classified 104 bilingual words with median cross-validated neural-only accuracy of 47.24%; language models then assembled sentences. It operated in successive 3.5-second windows, so “online” did not mean continuously streaming speech.
02Bilingual transfer remained single-participant
Bilingual transfer learning let neural data from one language improve decoding of the other, consistent with shared articulatory representations. Performance remained stable across a 30-day recording break without retraining, but this was still one participant and a constrained vocabulary.
03Inner speech is not unrestricted thought reading
Inner speech produced weaker but correlated motor-cortex patterns relative to attempted speech. Real-time decoding was demonstrated in three participants, using both 50-word and 125,000-word regimes; this was instructed, self-paced imagery, not unrestricted thought reading.
04A neural lock can suppress unintended output
The inner-speech study identified a neural motor-intent dimension separating imagined from attempted speech. An “imagery-silenced” training strategy suppressed unintended output, while a mental-keyword lock achieved 98.75% activation accuracy in one participant.
05Loudness intent appears before speech
In the 2026 loudness study, four attempted modes-mimed, whispered, normal and loud-were decoded offline with 94% and 89% accuracy in two participants. Intent-related preparatory signals crossed 80% accuracy 640 ms and 270 ms before speech onset, respectively.
06Buffer cadence is not response latency
The 2025 streaming system’s 80-ms increments are audio-buffer cadence, not total response latency. Median cue-to-output onset was 1.67 seconds for synthesized speech, and direct speech transcription had 40.8% median word error rate on its 1,024-word general set.
07Instantaneous output still had high error
The “instantaneous” 2025 intracortical system decoded intonation and short pitch sequences, but neural-only synthesized speech still had 43.60% word error rate. Simultaneous residual-speech biosignals did not explain the result: stethoscopic-microphone decoding had 100% word error rate in the reported comparison.
08Cross-participant transfer is not assistive use
Cross-participant transfer learning improved phoneme decoding across 25 speaking epilepsy patients and more than 3,600 sEEG electrodes. This is useful evidence for scalable model initialization, but it was not an assistive speech system demonstrated in an anarthric user.
If the remaining tests pass
Downstream capabilities, drawn dashed because they depend on results not yet in.
Who is building it-and what the money saysCapital, institutions and the global race
The teams doing the work, where they are based, and whether the money points to real delivery or only a plan.Company finance, public programmes, institutional leadership and market evidence-kept separate from valuations, forecasts and announced capacity.
Speech neuroprostheses now decode useful language in a few people, while companies are financing several competing implant routes. The commercial evidence is still early: registered studies often enroll only a handful of participants, and device designation or trial permission is not approval. Cursor control, decoded text and direct synthesized speech are kept distinct.
Who is building itCompanies, laboratories and programmes
Paradromics
USAHigh-data-rate intracortical Connexus BCI for communication and computer control
Precision Neuroscience
USAThin cortical-surface array intended to let people with paralysis control computers
Synchron
USA / AustraliaEndovascular BCI for digital-device control by people with paralysis
| Player | Country | What they are doing | Funding | Named investors | Source |
|---|---|---|---|---|---|
| Paradromicscompany | USA | High-data-rate intracortical Connexus BCI for communication and computer control Connect-One is an estimated two-person early-feasibility study, not an approved product. | Series A · $33M · May 2023 | Prime Movers Lab · Westcott Investment Group · Dolby Family Ventures · Green Sands Equity | Source · paradromics.com |
| Precision Neurosciencecompany | USA | Thin cortical-surface array intended to let people with paralysis control computers The company reports total funding; a take-home speech product has not been demonstrated. | $155M cumulativeSeries C · $102M · Dec 2024 | General Equity Holdings · B Capital · Duquesne Family Office · Steadview Capital | Source · globenewswire.com |
| Synchroncompany | USA / Australia | Endovascular BCI for digital-device control by people with paralysis Primarily a digital-control interface, not a high-bandwidth speech decoder. | $145M cumulativeSeries C · $75M · Dec 2022 | ARCH Venture Partners · Gates Frontier · Bezos Expeditions · Khosla Ventures | Source · businesswire.com |
| UCSF Chang Lab / BRAVOlab | USA | Develops speech neuroprostheses and direct brain-to-voice systems for people with paralysis | Not disclosed | Not disclosed | Source · changlab.ucsf.edu |
| UC Davis Neuroprosthetics Lablab | USA | Clinical intracortical research to restore rapid text and personalized synthesized speech | Not disclosed | Not disclosed | Source · health.ucdavis.edu |
| Utrecht CortiCom teamlab | Netherlands | 128-channel cortical communication study targeting independent home and keyword-speech use Registered estimated enrollment: two participants. | Not disclosed | Not disclosed | Source · clinicaltrials.gov |
Where every number comes from
13 sources — every figure on this page traces to one.
- Vidal's direct brain-computer communication proposalpubmed.ncbi.nlm.nih.gov
- Kennedy and Bakay locked-in cortical linkpubmed.ncbi.nlm.nih.gov
- 2009 review of speech communication BCIspmc.ncbi.nlm.nih.gov
- 2021 anarthria speech neuroprosthesisnejm.org
- 2023 large-vocabulary intracortical speech BCInature.com
- 2023 ECoG speech and avatar neuroprosthesisnature.com
- 2024 rapidly calibrating speech neuroprosthesisnejm.org
- 2025 streaming brain-to-voice neuroprosthesisnature.com
- 2025 instantaneous voice synthesisnature.com
- 2026 long-term independent home usenature.com
- BrainGate interim safety profilepmc.ncbi.nlm.nih.gov
- Paradromics Connect-One first implantuofmhealth.org
- Connect-One registered study and completion datesclinicaltrials.gov