A useful transcript lets you return to the words that matter: a name, a decision or the reason a plan changed. Testing a local recorder should follow that whole journey, from capture to a readable note on your computer. This guide explains the checks behind that goal, including recovery, audio retention and the privacy boundary.

This is a validation guide, not a published C1 benchmark report. The scenarios below describe acceptance checks; they do not claim measured results for every condition.

What is the system under test?

The approved C1 architecture divides work across two devices. C1 performs capture and on-device voice activity detection, stores encrypted audio slices temporarily, and transfers over Bluetooth or USB-C. The paired macOS or Windows computer performs local ASR and speaker labeling, writes local OKF Markdown, and instructs C1 to delete each slice after transcription consumption.

This state model covers temporary device-side capture and transfer slices. It does not define the retention of saved original recordings: users choose in OneMira Settings whether to keep that audio. Test that choice separately, so clearing a consumed transfer slice is not mistaken for deleting every copy of the recording.

That boundary creates at least six observable states:

  1. Captured: a complete or recoverable slice exists on C1.
  2. Staged: the computer has copied the slice but has not committed a note.
  3. Transcribed: ASR produced candidate text.
  4. Committed: the Markdown note and its metadata are durably written.
  5. Acknowledged: the sync state records that the slice was consumed.
  6. Released: C1 deleted the source slice.

The destructive transition is last. If a process crashes between staging and commit, the source must remain recoverable. If commit succeeds but deletion acknowledgement is lost, the next run must identify the already-consumed slice and avoid a duplicate note.

How should the interruption matrix be tested?

Inject failure at every boundary, then verify both sides. “The app recovered” is not enough; compare file hashes, note counts, device inventory, and state pointers before and after restart.

Injected failure Expected device state Expected computer state
Power loss during capture Earlier slices intact; active slice complete or explicitly marked invalid No fabricated note
Disconnect during transfer Source slice retained Partial staging file ignored or resumed
Process killed during ASR Source slice retained No committed duplicate; retry allowed
Power loss during note write Source slice retained Atomic write leaves old state or complete new note
Disconnect after commit, before delete Source may remain Processed hash prevents retranscription; delete can retry
Corrupted slice Not deleted until a local quarantine copy is verified Error and source provenance preserved

How do you validate transcription without inventing one accuracy number?

Word error rate is useful for a fixed labeled corpus, but it can hide the errors that matter to work. Build a versioned evaluation set containing quiet speech, low-volume speech, keyboard noise, accents and supported languages, overlapping speakers, domain terms, names, dates, numbers, and negation. Keep the hardware placement and source level recorded with each sample.

Report at least three layers:

  • WER or CER on the labeled corpus, with model and decoder versions.
  • Critical-term recall for identifiers, numbers, names, and negative instructions.
  • Task usability: whether a reviewer can derive the intended decision without replaying the entire recording.

Do not compare two ASR systems on different audio, language settings, or post-processing rules.

What does VAD validation need to measure?

Voice activity detection changes what reaches ASR. An aggressive threshold can clip quiet syllables or the start of a sentence; a permissive threshold can retain long noise regions. Test false rejection, false acceptance, boundary truncation, and fragmentation against labeled time intervals. Then inspect the downstream transcript, because a small timing error may delete a critical negation even when aggregate VAD metrics look acceptable.

C1's saved original recordings use stereo WAV format. That does not establish the codec, sample rate, or bit depth of internal transfer or processing data. For decoder tests, document the actual format and settings of each fixture, then verify duration, channel count, and end-to-end integrity on the files being tested. RFC 6716 is a reference for Opus test cases, not evidence of C1's internal configuration.

Macro view of the Silver White C1 upper rear corner, with a curved metal edge and clear cover at the right.
A close look at C1's metal edge, white rear panel, and clear cover.

How should privacy claims be verified?

“Local” is an architecture claim that can be tested. Capture DNS and network traffic while recording, transferring, transcribing, searching, and exporting. The OneMira product claim is narrower than “nothing ever uses the internet”: OneMira speech recognition and transcription run on the paired computer, while any third-party AI service selected by the user follows that provider’s data path.

A privacy test should therefore record:

  • which process opens each network connection;
  • whether audio bytes or only update/telemetry metadata leave the machine;
  • where temporary audio, model caches, logs, and transcripts are stored;
  • when device and local temporary files are deleted;
  • whether a third-party agent receives a selected excerpt or the full note.

Local processing can reduce one class of cloud exposure, but it does not automatically satisfy GDPR, HIPAA, employment policy, or recording-consent law. Compliance depends on purpose, consent, access control, retention, jurisdiction, and the downstream tools used.

What evidence closes DVT?

For every requirement, retain the test version, device and software build, input fixture, expected result, measured result, logs, hashes, screenshots where useful, and disposition. Re-run the matrix on both supported operating-system families. A passing happy path on one powerful computer does not validate recovery, low-resource behavior, or another platform.

The troubleshooting documentation should map user-visible errors to these states. Production repeatability then moves to the PVT guide.

What does local processing mean for your day?

With C1 and OneMira Desktop, your Mac or PC handles transcription and the included local AI can turn conversations into notes and mind maps. After the required downloads, you can use that path offline without a OneMira account or subscription. Choose in Settings whether to keep the original recording as stereo WAV, alongside editable local notes.

Explore C1 for conversations you can return to, or see the AI notes and models guide for the available processing paths.

Sources and further reading