Evidence, with boundaries
Benchmarks that say what they measured.
A speech model number is not the same thing as release-to-insert latency. We publish the scope, hardware and exclusions so you can compare results without a marketing shortcut.
Current measured result
| Metric | 150 ms median local ASR inference |
|---|---|
| Corpus | 188 English clips |
| Hardware | M4 MacBook Air |
| Included | Model transcription inference for the prepared clip |
| Excluded | Recording, audio-tail capture, cleanup, target validation, accessibility insertion and clipboard fallback |
Local ASR inference only. It excludes recording, audio-tail capture, cleanup, accessibility insertion, and clipboard fallback.
Reliability suites
The automated corpus includes 120 silence cases and 24 cleanup safety dimensions. The application also exercises ordered commits, retention, interrupted journals, hotkey state, fidelity fallback and insertion policy. Counts can grow; behavior and failure policy matter more than a frozen test total.
Why there is no release-to-text claim yet
Release-to-insert latency is not yet published because the signed-build hardware matrix is still a release gate. That matrix must cover clean installs, permission denial and recovery, microphone changes, long and overlapping dictations, secure fields, custom web editors, terminals, clipboard restoration, sleep and wake, offline use, provider failure, update installation and uninstall behavior.
Acceptance rule
A result cannot be promoted to the landing page unless the artifact, corpus revision, machine, percentile, sample count and measurement boundaries are recorded together. Failed cleanup is a fallback result, not a silent pass. Failed insertion must leave recoverable text on the clipboard and visibly tell the user.