SaypeBetaDownloadsv0.1.0Private offline dictation · Linux, Windows & Mac
Private, offline dictation — your words never leave the room.
Cloud dictation uploads every word. Saype (say + type, pronounced “sayp”) doesn't: press a hotkey, speak, and a blind typer emits only your transcript at the cursor in any app. True streaming Nemotron 3.5 — words land as you speak, not after you pause. Super fast, fully offline, 90%+ right first time on clear speech — the rest fixed live by Backspace revision — and a Whisper mode hits 95%+ on the toughest audio.
one-time · GST included · FOUNDER BETA — FIRST 100 FREE
14-day money-back guarantee — if it doesn't hear you, email for a refund, no forms.
Founder beta: free for the first 100 before it goes to ₹1,500. Whisper mode covers 95%+ accuracy tasks today; word boosting is included.
Launch video · ~2 min tour
The full tour in one film: sub-second CPU streaming, the pill at work in any app, the speed⇄accuracy slider, Whisper mode, word boosting, and the one-time price.
- 01Words appear while you're still speaking — interim results, typed live.
- 02When you pause, the endpoint finalizes the sentence.
- 03If the model revises itself, it Backspaces only the changed tail and retypes — same blind-typer channel, nothing else it can do.
Why it's different
- 01
Private offline dictation on Linux, Windows, and Mac
Local streaming transcription, typed at your cursor through the OS-approved channel. Cache-aware RNNT processes each new chunk once — no overlapping recompute — so latency stays sub-second on CPU. One hotkey flow on all three OSes; no other offline option covers them all.
- 02
Blind typer: emits only your words
Only transcript characters plus Backspace for corrections. No uinput, no evdev, no keylogging, no shortcuts — holding Ctrl/Alt/Super/Shift safely skips instead, the text waits in history. Your clipboard is never touched.
- 03
No account, no cloud, no calling home
Fetch the ~1 GB voice model once, then fully offline. Decline the input permission and it still works, history only — your clipboard is never overwritten.
Only your transcript. Nothing else.
NEVER: UINPUT / EVDEV · KEYLOGGING · RETURN SYNTHESIS · CLOUD AUDIO
Pricing · one-time
Own it once. No subscription.
Cloud dictation costs $12–15/mo forever. Saype is one payment, priced fairly for your region — shown automatically below.It's free during the founder beta; everyone after pays ₹1,500. Refunds revoke the license key and the app stops activating — your audio never left your machine either way.
one-time · GST included · FOUNDER BETA — FIRST 100 FREE
14-day money-back guarantee — if it doesn't hear you, email for a refund, no forms.
Roadmap · free for owners
- 01
Whisper mode for 95%+ accuracy — available now
Switch to --model whisper for large-v3-turbo accuracy on tough audio, fully offline — plus translate. Pastes land every ~2s.
- 02
Word boosting for Nemotron — available now
Teach it your names, terms, and jargon so streaming gets your vocabulary right the first time. Included, no extra cost.
FAQ
What makes Saype a private dictation app?
Saype transcribes entirely on your machine. Audio is never uploaded, there is no account, and the blind typer emits only transcript characters plus Backspace — no uinput, evdev, keylogging, or clipboard access.
Which operating systems does Saype support?
Saype is available for 64-bit Linux (AppImage, deb, rpm), Apple Silicon macOS (DMG), and 64-bit Windows (MSI). One hotkey flow works across all three.
Does Saype work offline?
Yes. Download the roughly 1 GB voice model once, then dictation works fully offline forever — no cloud, no network calls, no account.
How is Saype different from Wispr Flow or Superwhisper?
Cloud dictation uploads every word and charges a subscription. Saype runs Nemotron streaming locally on the CPU, covers Linux, Windows, and Mac, and is a one-time purchase instead of a monthly fee.
Is Saype free right now?
Yes. The first 100 founder-beta users get Saype free. After the founder beta it is $29 USD or ₹1,500 INR one-time, tax included.
Can I dictate into any app or terminal?
Yes. Words are typed at your cursor in editors, browsers, chat, documents, and terminals — Saype uses the OS-approved input channel, not synthetic return presses or clipboard tricks.
Requirements
- 0164-bit Linux, macOS, or Windows
- 02A microphone — built-in is fine
- 03~1 GB free disk for the one-time voice-model download
- 04Internet once, to fetch the model — fully offline after that
Accuracy figures are founder-measured across real dictation sessions, counted harshly — expected errors per 100 words on clear mic speech. Measured WER bench to follow.
Guides