Skip to content
Mohsen Seyedkazemi Ardebili edited this page Jul 31, 2026 · 1 revision

FAQ

Is it really offline? Does any audio leave my machine?

Yes, it's fully offline, and no. Transcription runs locally with faster-whisper; there are no network calls in the dictation path, no API key, and no account. You can confirm with yazses doctor (it reports "fully offline") and by watching your network — there's nothing to see.

How is this different from Wispr Flow, Talon, or the built-in OS dictation?

  • vs. cloud dictation (Wispr Flow, Google/Apple/MS): YazSes runs entirely on-device — nothing is uploaded. That's the whole point.
  • vs. Talon Voice: Talon is a powerful scripting/accessibility platform with a learning curve. YazSes aims at plug-and-play dictation + simple voice commands. Different goals; both valid.
  • vs. built-in OS dictation: YazSes is cross-platform, open source, private by construction, scriptable, and works into terminals and editors.

What accuracy / speed can I expect?

It depends on the Whisper model you choose (smaller = faster, larger = more accurate) and your CPU. The defaults target a good balance on a typical laptop CPU with int8 quantization — no GPU required. If dictation feels off, yazses tune and yazses mic-level help you calibrate.

Dictation "stopped writing" / my first words get cut off / it discards audio as silent

Almost always one of:

  • Mic level below the VAD threshold → run yazses mic-level --set to recalibrate.
  • The OS default mic switched (e.g. a USB-C monitor stole capture) → the mic-change guard auto-heals, or pin your mic with yazses audio use <name>.
  • First words clipped → there's a pre-speech padding setting; see docs/.

yazses doctor --mic diagnoses most of these.

Does it support languages other than English?

The defaults are tuned for English (.en Whisper models), but faster-whisper ships multilingual models you can select via config. Better multilingual support and code-switching are active roadmap items — this is a great area to contribute. See Ideas.

Does it work on Wayland?

Dictation and injection work across X11 and Wayland (with the right injector — yazses doctor checks readiness). Some features that need to focus another window (like look-to-pane targeting) are X11-only today, because Wayland restricts cross-window control. Improving the Wayland story is on the roadmap.

macOS / Windows — are they as good as Linux?

The architecture is cross-platform (shared Protocol interfaces with per-OS backends) and CI runs on all three. Linux is the most battle-tested day to day; helping harden macOS/Windows is high-value and very welcome — see Contributing.

What are all these "off by default" features?

YazSes has a large catalogue of advanced, opt-in capabilities (voice commands, meeting capture, offline file transcription, accessibility modes, and experimental perception features). They stay dormant until you run yazses features enable <name>, so a fresh install is simple and nothing changes your setup unless you ask. Browse them with yazses features.

How do I contribute?

Start at Contributing — Start Here. Pick a good first issue, or open an Idea. Small PRs and docs fixes are genuinely welcome, and we review fast.

Where do I report a bug or ask a question?

  • 🐞 Bug → open an issue with your OS, yazses --version, and yazses doctor output.
  • Question / how-toQ&A discussions.
  • 🔐 Security → see SECURITY.md; please don't file security issues publicly.