Spokenly for Linux
Spokenly for Linux is a dictation app with local and cloud speech to text, AI text processing, and support for 100+ languages, now available on the Linux desktop.
Updated July 2026
Direct download · amd64 deb, x86_64 rpm, and x86_64 AppImage
Free speech to text software for Linux
Linux has always had powerful speech recognition engines, but very few polished dictation apps. Spokenly closes that gap: press a hotkey, speak, and accurate text appears in whatever app you are using, including browsers, IDEs, terminals, email, and chat.
You choose how transcription runs. Local Whisper and Parakeet models process everything on your machine, free forever, with full privacy and offline support. Or connect cloud engines like Deepgram and OpenAI with your own API keys at no extra cost, or through a Spokenly Pro subscription.
After transcription, built-in AI text processing removes filler words, fixes punctuation, and reformats what you said. A rambling thought becomes a tidy email, a bug report, or a commit message with a single mode.
What you get
Free with local models and BYOK
- Local models (Whisper, Parakeet) that run fully offline on your machine
- Cloud models (Deepgram, OpenAI, Soniox, ElevenLabs) for maximum accuracy
- 100+ languages with real-time streaming and file-based transcription
- Bring your own API keys from 11 providers at zero cost
- AI text processing with modes and AI Instructions (GPT-4, Claude, Gemini, Grok, local LLMs via Ollama)
- Global hotkey, recording overlay, and system-wide text insertion
- Works on both X11 and Wayland
- Auto-updates from inside the app
Voice typing across supported Linux desktop apps
Spokenly is system-wide: it returns text to the focused app. Dictate a pull request review in the browser, comments in your editor, a message in Slack or Discord, or a document in LibreOffice. Password fields, sandboxed apps, and compositor-specific input restrictions may behave differently, so test the target apps in your own session.
A global hotkey starts and stops recording, and a small overlay shows that Spokenly is listening. There is no separate window to copy text out of. Your words land directly in the app you are working in, on both X11 and Wayland.
Transcribe audio and video files on Linux
Beyond live dictation, Spokenly converts pre-recorded audio and video to text. Drop in MP3, WAV, M4A, or MP4 files and get clean transcripts for interviews, lectures, voice memos, and meeting recordings.
Packages for supported x86_64 Linux systems
Spokenly for Linux ships in three x86_64 formats: an amd64 deb, an x86_64 rpm, and an x86_64 AppImage. Current requirements list Ubuntu 24.04+, Fedora 40+, Debian 13+, or compatible x86_64 distributions. ARM64 builds are not currently listed.
How Spokenly compares to other Linux dictation tools
Until now, dictation on Linux mostly meant do-it-yourself tooling. nerd-dictation is a capable command-line tool, but you assemble the pieces yourself: models, hotkeys, and text injection. Desktop tools like Speech Note focus on transcription in their own window rather than typing into every app. Open-source Handy runs on Linux and shares the local-first idea, but stays deliberately minimal.
Wispr Flow, Superwhisper, and MacWhisper never shipped Linux versions. Spokenly brings that class of dictation experience to the Linux desktop, with the same features as our Windows and macOS apps.
For a tool-by-tool view of local engines, desktop apps, browser options, and terminal workflows, see the speech-to-text tools for Linux comparison.
Frequently Asked Questions
Is Spokenly available on Linux?
Yes. Spokenly for Linux is generally available for x86_64 systems as amd64 deb, x86_64 rpm, and AppImage packages. ARM64 packages are not currently listed.
Is Spokenly for Linux free?
Yes. Local models and your own API keys (BYOK) are free with no account required, the same as on macOS and Windows. Pro features that use Spokenly cloud transcription require a subscription.
Does Spokenly work offline on Linux?
Yes. Local Whisper and Parakeet models run entirely on your machine, so dictation keeps working without an internet connection and no audio ever leaves your computer.
Does Spokenly support Wayland and X11?
Yes, Spokenly supports both X11 and Wayland. Global shortcuts and synthetic text insertion vary by compositor and target app, so test the current build with the desktop and apps you rely on.
Is there a Wispr Flow for Linux?
No. Wispr Flow runs on macOS, Windows, and iOS but has no Linux version. Spokenly brings the same kind of system-wide dictation to Linux and adds free local models that run offline.
Is there a Superwhisper for Linux?
No. Superwhisper is available for macOS, Windows, and iOS, but not Linux. If you are looking for a Superwhisper alternative on Linux, Spokenly offers local Whisper transcription plus cloud models and AI text processing.
Does Dragon NaturallySpeaking work on Linux?
Nuance has never released Dragon for Linux, and running the Windows version through Wine is unreliable. Spokenly gives you native speech to text on Linux with local models and modern cloud engines.
Which Linux distributions does Spokenly support?
Current x86_64 downloads include an amd64 deb for compatible Debian-based distributions, an x86_64 rpm for compatible rpm-based distributions, and an x86_64 AppImage. The download page lists Ubuntu 24.04+, Fedora 40+, Debian 13+, or compatible distributions as current requirements.
Dictate at the speed of speech on Linux
Free with local models. No account required.
Download for Linux