Talk. Bulbul types.
A free, open-source Windows dictation app. Hold a hotkey, speak, release — cleaned-up text lands where your cursor already is.
irm https://bulbultypes.xyz/install.ps1 | iexWindows 10 / 11 · x64 today · Mac and Linux coming
Three things, done quietly well.
No commands to memorize, no dashboard to babysit. Hold, talk, and clean text appears where your cursor already is.
Hold-to-talk, anywhere
Press and hold your hotkey in any window. Bulbul captures while you speak and stops the moment you let go.
Cleanup happens automatically
Filler words, false starts, and stray “ums” are removed. What lands is the sentence you meant to say.
Learns your corrections
Fix a word once and Bulbul remembers. Names, jargon, and product spellings get more accurate over time.
From the way you talk to the way you write.
Speech is messy — restarts, hedges, “ums.” Bulbul rewrites it into the sentence you intended, then pastes that.
So, um, I basically wanted to, you know, follow up about the, uh, the proposal — and honestly I think we should just ship it.
I wanted to follow up about the proposal — I think we should ship it.
Hold, speak, release.
The whole interaction is three moves. Everything technical happens in the half-second between letting go and seeing your words.
- 01
Hold the hotkey
Press and hold from inside any app — no window switching.
Ctrl+Win - 02
Speak naturally
Talk the way you think. Bulbul listens until you release.
- 03
Release — it’s pasted
Cleaned text drops straight into the field you were in.
Pasted
- 01Captured locally
Audio stays on your machine via cpal.
- 02Transcribed
Groq Whisper, using your API key.
- 03Cleaned up
An 8B-class model polishes the text.
- 04Pasted in place
Inserted where your cursor already is.
Same hold-to-talk. Any window.
Bulbul types into whatever already has focus — your mail client, your editor, your chat box. Pick a destination and watch.
More than a microphone button.
Everything is built around one loop — speak, clean, paste — then sharpened with the tools that make daily dictation actually stick.
Teach it once. It remembers.
Fix a name or a piece of jargon a single time and Bulbul keeps it. Your personal dictionary builds itself from the corrections you actually make.
Reshape text, not just dictate it.
Captured something rough? Expand a bullet into a paragraph, reformat a list, or refine a draft — without leaving the app you’re in.
Hold-to-talk dictation
Press and hold to capture, release to insert.
Speak raw, paste polished
Hold the hotkey and just talk — Bulbul pastes the cleaned-up, polished version, never the raw transcript.
Per-app context
Tone adapts — terse in chat, fuller in mail and docs.
Snippets
Reusable blocks — signatures, boilerplate — dropped in by voice.
Scratchpad
A local holding space for dictations before they land.
Insights
Words dictated, time saved, and your most-made corrections.
A trust ledger, not a privacy promise.
The honest version of “your data is safe”: here is exactly where everything goes, line by line.
Bring your own Groq key
BYOKYou supply the API key. Bulbul never ships or proxies one for you.
No Bulbul servers
directAudio goes from your machine straight to Groq. There is nothing in the middle to trust.
Local-first storage
SQLiteHistory, snippets, and settings live in a SQLite file on your PC — not a cloud account.
Signed releases
minisignEvery build is signed with minisign so you can verify exactly what you’re running.
Anonymous usage stats are on
on by defaultBulbul is solo-built — counts and error categories help me know what to fix. Never your transcripts, audio, dictionary, or which app you’re typing into. Turn it off anytime in Settings → Privacy.
Source available
openThe code is on GitHub. Read the data path and audit it for yourself.
Where Bulbul fits.
A plain-language comparison. Bulbul’s column is what ships today; other columns reflect general, well-known traits — check each tool for specifics.
- Bulbul
- Windows Voice Typing
- Wispr Flow
- Whisper wrappers
- Bulbul
- Windows Voice Typing
- Wispr Flow
- Whisper wrappers
- Bulbul
- Windows Voice Typing
- Wispr Flow
- Whisper wrappers
- Bulbul
- Windows Voice Typing
- Wispr Flow
- Whisper wrappers
- Bulbul
- Windows Voice Typing
- Wispr Flow
- Whisper wrappers
- Bulbul
- Windows Voice Typing
- —
- Wispr Flow
- Whisper wrappers
- Bulbul
- Windows Voice Typing
- Wispr Flow
- Whisper wrappers
- Bulbul
- Windows Voice Typing
- —
- Wispr Flow
- —
- Whisper wrappers
- —
- Bulbul
- Windows
- Windows Voice Typing
- Windows
- Wispr Flow
- Mac · Win
- Whisper wrappers
- mostly Mac
varies by tool · Comparison is informational, not a benchmark.
Honest engineering, all the way down.
If you’re going to inspect it, here’s the stack. Native where it matters, open where it counts.
A native webview shell — not Electron. Small binary, low memory.
Audio capture, global hotkeys, and the local store run in Rust.
The interface is React 18, bundled and served by Vite.
Global hotkeys and paste-at-cursor go through native Win32.
Microphone capture via the cross-platform cpal audio crate.
Transcription on Whisper, cleanup on an 8B-class model.
Every local record lives in a single SQLite database file.
Signed builds with a signature-verifying auto-updater.
Up and running in a minute.
Download the signed installer, or paste one line into PowerShell. Windows 10 / 11 · x64.
irm https://bulbultypes.xyz/install.ps1 | iexOn first run, Bulbul asks for your name and your Groq API key. That’s the whole setup — no account, no sign-in.
Questions, answered plainly.
No. There’s no sign-up and no login. On first run it asks for your name and your Groq API key, and that’s it.