DUNIN7 · LOOMWORKS · RECORD
record.dunin7.com
Status Current
Path change-requests/cr-2026-146-retain-live-dictation-audio-v0_6.md

CR-2026-146 — Retain Audio for Live-Dictation Voice Captures — v0_6

Version: 0.6 (adds to v0.5 — see below) Status: Scoped, ready for a follow-on build brief. v0.1–v0.3 already built and merged. Repos: loomworks-engine, loomworks

Addition to v0.5

v0.5 fixes what happens when live transcription fails or the capture is confused mid-speech. This adds a separate, upfront option: let the Operator disable interpretation entirely before speaking — useful when transcription is known in advance to be unreliable (e.g. speaking a language the recognizer does not support, such as some indigenous languages). With interpretation disabled, the held item is created with placeholder content and the recording only, reviewable via Replay.

What this adds

A "disable interpretation" toggle on the voice-capture control. When enabled, live transcription is skipped entirely — only the audio recording happens. The resulting held item shows placeholder content (e.g. "Voice note — not transcribed") rather than an empty or garbled transcript, with Replay as the primary way to review what was said.

Comment field — required alongside the placeholder

Operator requirement: a voice-only held item with no transcript cannot later be found by search or recall — there is no text content to match against. The held item must carry an Operator-typed comment field (not a transcript — a short label or note the Operator supplies) so the item can be located and categorized later when the recording is being evaluated. This is separate from the placeholder content; the placeholder marks the item as untranscribed, the comment is what makes it findable.

Seed check

No conflict. Operator-authority: the Operator chooses upfront whether to attempt interpretation. "Only show what is available": the toggle is a real, working option, not a placeholder control. The comment requirement supports the seed's Memory framing — accumulates with provenance — provenance here includes the Operator's own labeling of content the system could not itself describe.

Out of scope

Any change to Web Speech's own recognition accuracy. The v0.5 failure-path fix (Replay on failed/garbled transcription) — this is a separate, additive control for when the Operator chooses not to attempt transcription at all.