CLASSEVE
RouteHome
Best of · facts checked 2026-09-05

The best dictation software for Linux

Linux is the platform most dictation apps skip. Of the products compared on this site, Wispr Flow, Typeless, Superwhisper, SuperDictate, Whisperstream and Dragon do not ship for it. Three do: Lven Instant, on-device with a published speed measurement, unlimited, on X11 and Wayland; Lven Cloud, the same bubble with server-side transcription at $3.49 a month billed yearly; and OpenWhispr, free and open source if you manage Whisper models yourself.

Scored on
  1. Ships for Linux at all
  2. Where the audio is processed
  3. X11 and Wayland support, and how insertion works on each
  4. Package formats and what the distribution must provide
  5. Price and limits
The ranking

  1. Lven Instant

    ClassEve

    The only paid dictation product compared on this site that is always on-device, never rewrites your words, has no usage cap and ships on Linux — and after two months of membership the builds are yours to keep.

    Right for: Daily dictation on a Linux desktop, offline, as a .deb, AppImage or tarball; no root.

    Where it transcribes
    On your device — nothing uploaded
    Your words
    Typed as said, punctuated, never rewritten
    Speed and accuracy
    RTF 0.166 — about six times faster than realtime — 3.76% word error rate on clean speech, measured on consumer-grade hardware, 73 clips, 2026-07-23.
    Limits
    None
    Platforms
    Windows, Linux, Android
    Price
    $10/mo or $95/yr, five devices, every local ClassEve app; yours after two months. Early-access price if you start before 15 October 2026: $10 a month for the first 3 billing months, then $20; or $95 for the first year, then $190.

  2. Lven Cloud

    ClassEve

    The same bubble and hotkey with the transcription done on our servers — for the device that cannot run a local model — at a third of Wispr Flow's price, with no word cap, no rewrite, and nothing kept after delivery.

    Right for: A Linux machine too small for the local model.

    Where it transcribes
    On ClassEve's servers; audio and text not kept after delivery
    Your words
    Punctuated, never rewritten
    Limits
    No daily cap on a paid plan
    Platforms
    Windows, Linux, Android
    Price
    From $3.49/mo billed yearly, $7.99 monthly; included with Premium

  3. OpenWhispr

    Free, MIT-licensed Whisper dictation that runs offline, for people happy to manage models themselves. On the same hardware where Lven's engine runs six times faster than realtime, whisper-large-v3 never reaches it.

    Right for: Free and open source above everything, and comfortable troubleshooting models and configs yourself.

    Where it transcribes
    On-device (Whisper)
    Platforms
    Windows, macOS, Linux (per its site). No Android.
    Price
    Free, MIT
    Support
    Community and repository issues
FAQ

Common questions.

Does Wispr Flow work on Linux?
No. Wispr Flow ships for macOS, Windows and iPhone. Neither do Typeless, Superwhisper, SuperDictate, Whisperstream or Dragon. Lven Instant and Lven Cloud do, and OpenWhispr lists Linux on its site.
Does dictation work on Wayland?
Yes. Lven Instant inserts text the same way on X11 and Wayland. Wayland does not give an application a global shortcut, so you bind lven-linux --toggle in your compositor; on X11 the app holds Super+Space itself.
Which distributions are supported?
Any 64-bit distribution with glibc 2.34 or newer — Ubuntu 22.04 and later, Debian 12, Fedora 35 and later — with PipeWire or PulseAudio. Everything the app needs, speech engine included, ships inside the package.
Sources
  1. Wispr Flow pricing page — Pro $15/user/mo monthly or $12/user/mo billed annually; free tier 2,000 words/week on desktop
  2. Digital Trends — Wispr Flow traces accuracy complaints to an over-aggressive Auto Cleanup that changed words
  3. Typeless — home page and pricing page: Mac, Windows, iOS and Android; polished-writing rewrite; free tier 8,000 words/week; $12/member/mo billed yearly, $30 monthly
  4. Superwhisper — AI voice to text for macOS, Windows and iOS; offline and cloud models
  5. ClassEve — server vs on-device dictation engines, measurement on consumer-grade hardware (RTF, WER, latency)
  6. ClassEve — What the polish pass changes: the 31-case golden corpus
Head to head
What is on-device speech to text?
Lven Instant vs. OpenWhisprLven Instant vs. Wispr FlowLven Instant vs. Superwhisper
We use local storage for sign-in. Accepting keeps you signed in between visits. We do not run ads or third-party trackers; we count page views ourselves, without cookies or identifiers. See our privacy policy.