https://fisper.app

Local Voice-to-Text for macOS | Fisper - Free Whisper DictationFree voice-to-text dictation for macOS. Press a hotkey, speak, and text appears anywhere. Powered by Whisper on Apple Silicon - 100% local, no cloud.Local Voice-to-Text for macOS | Fisper - Free Whisper DictationFisperFeaturesSetupConfigurationTerminalPrivacyChangelogDownloadYour voice,typed outeverywhere.Press a hotkey in any macOS app. Speak naturally. Watch your words appear in real time. All transcription happens locally on Apple Silicon.Download FispermacOS 14+·Apple Silicon·Free foreverFeaturesSystem-Wide DictationWorks in any macOS app - browsers, text editors, Terminal, Slack, Messages. Text is injected wherever your cursor is focused.Real-Time StreamingLive mode shows text as you speak. Only the changed parts update - no flickering, no jumping.100% Local ProcessingRuns AI speech models directly on Apple Silicon. No cloud requests. No API keys. No internet required.Speed vs. AccuracyThree models to match your needs: base (~150 MB) for speed, small (~500 MB) for balance, or large-v3-turbo (~3 GB) for maximum accuracy.Configurable ShortcutsF5, ⌥Space, double-tap Right ⌘, and more. Seven options so you never clash with existing bindings.Menu Bar ResidentNo dock icon. No main window. Sits in your menu bar, invisible until you need it. A floating HUD shows recording state.Setup01InstallDownload the DMG. Drag Fisper to Applications. Open it from your menu bar.02PermitGrant Microphone and Accessibility access in System Settings. Fisper detects the change instantly - no restart needed.03DictatePress F5 (or your preferred shortcut) in any application. Speak naturally. Your words appear at the cursor in real time.ConfigurationEverything is configurable from the menu bar. Pick a Whisper model based on your speed and accuracy needs, switch between live streaming and batch transcription, and choose a global shortcut that fits your workflow.Built for Terminal AgentsEnable "Auto Submit in Terminal" in settings and Fisper detects when your cursor is in a terminal. When you stop recording, it automatically transcribes and submits the message - perfect for working with Claude Code and other terminal-based AI agents.PrivacyNothing leavesyour machine.Every syllable is processed on-device by Apple Neural Engine. Audio samples live only in memory during transcription. There are no accounts, no analytics, no telemetry, no cloud.✓No cloud processing✓No API keys or accounts✓No internet required✓No analytics or telemetry✓No audio stored on diskFAQIs Fisper really free?Yes. No trials, no subscriptions, no in-app purchases. Free forever.Does it work without an internet connection?After the initial model download, everything runs on-device. Turn off Wi-Fi and it works the same.Which Macs are supported?Any Apple Silicon Mac (M1 or later) running macOS 14 Sonoma or newer. Intel Macs are not supported because Whisper models require the Neural Engine.Which languages does it support?English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Hindi, Turkish, Ukrainian, Polish, Dutch, and Russian. You can also set it to auto-detect.How accurate is the transcription?Depends on the model. Large-v3-turbo rivals cloud services. Base is faster but less precise. Pick the trade-off that works for you.Why does Fisper need Accessibility permission?It types text by simulating keystrokes into whatever app is focused. macOS requires Accessibility access for that. Without it, Fisper can record but cannot inject text.Will it conflict with macOS built-in dictation?Not if you pick a different shortcut. The default F5 does not clash with Apple's dictation trigger. Six other hotkey options are available.How much disk space do the models need?Base is ~150 MB, Small is ~500 MB, Large-v3-turbo is ~3 GB. Models are downloaded once and cached locally.Release Notesv1.0.1February 8, 2026–Updated app icon and refined color palettev1.0.0Initial ReleaseFebruary 7, 2026–System-wide voice dictation on macOS using local Whisper models–Live streaming mode - text appears as you speak in real time–Batch mode - transcribe everything after recording stops–Three model tiers: base (~150 MB), small (~500 MB), large-v3-turbo (~3 GB)–Seven configurable global shortcuts (⌥Space, F5, Right ⌘×2, and more)–Terminal auto-submit - press hotkey, speak, command executes automatically–Menu bar app with floating pill-shaped HUD overlay–Auto-updates via Sparkle - always on the latest version–100% local - no cloud, no accounts, no internet requiredDownloadStop typing what you could just say. Stop sending your voice to the cloud.StartspeakingDownload. Permit. Press F5.Three steps. No accounts. No signup. No setup beyond that.Download FispermacOS 14+·Apple Silicon·Free foreverCopyright © 2026 Fisper byenen1789393686https://fisper.app

Editja s-sit tiegħek?

X'qed tagħmel?