Skip to content

YazSes v2.2.0-dev.1 — Wave F ship-now tier (developer preview)

Pre-release · not published (publish workflows are pinned to v0.x/v1.x; v2 dev tags do not ship). v1.4.1 remains the stable release. Every feature is OFF by default.

Opens Wave F — a fresh 2026 SoA round (10 candidate features distinct from the prior 34) in design/vision/v2-research/08-wave-f.md + design/adr/adr-v2-035..038. The four ship-now, fully-pure features (no new dependency):

New features (all off by default)

  • Speaking Coach (ADR-v2-035, [coach]) — private on-device analytics of your dictation: filler-word rate, words-per-minute, vocabulary diversity. Owns the on-device niche the cloud coaching apps don't. Data from the opt-in encrypted corpus only.
  • Smart-Paste (ADR-v2-036, [smartpaste]) — adapts injected syntax to the target app (markdown bullets, code casing, URL autolinking) using local window metadata.
  • Audio-Anchored Scrubbing (ADR-v2-037, [scrub]) — keeps word-level timestamps so you can replay what you said or pick a word to re-dictate just that word.
  • Dictation Reflow (ADR-v2-038, [reflow]) — say "structure this" to rewrite a ramble into bullets and action-item checkboxes. Pure heuristic; a local SLM refines it via an extra.

yazses features now lists 49 capabilities.

Wave F backlog (medium / hardware-gated)

Acoustic Context Profiles, Personal Read-Back Voice, Mood Ledger, Pronunciation Feedback, Gesture Chords, Two-Way Live Interpreter.

Quality

1060 tests green across Linux × macOS × Windows on Python 3.11 and 3.12. Every Wave F ship-now core is unit-tested to 100% with no new dependency; the default install and v1 dictation path are unchanged.