Stays on your Mac
Built in models transcribe your speech on your Mac, with no account and no cloud fallback. Models download once, then work offline.
Open source dictation for Mac
Speak it messy.
Send it clean.
Hold ⌥ Space in any app and just talk. BetterWispr drops the ums and false starts, spells names your way and writes in the style you set for each app. Speech stays on your Mac.
Free · macOS 14+ · Apple Silicon recommended
- No account
- Local speech models
- Meeting notes built in
Typing0.0s0 wpm
Can we move the design review to Thursday at 3?
BetterWispr0.0sListening
Can we move the design review to Thursday at 3?
Speak in any app. BetterWispr handles the rest.
Hold to talk
Hold ⌥ Space while you speak and let go to finish. Switch to press to toggle, or record any shortcut with ⌘, ⌥ or ⌃, or an F key.
Pick your model
Nine built in models from Apple speech, Parakeet and Whisper. Parakeet covers English, Japanese and 25 European languages, and Whisper covers more. Or choose your own Sarvam AI, Smallest AI or OpenAI compatible API.
Meeting notes
Notetaker transcribes your mic as Me and other apps as Them, next to your own notes. Apple Intelligence or Ollama then writes the summary, decisions and action items on your Mac.
A style for every app
Set a tone for personal chats, work apps, email and everything else. Casual drops the final period, very casual drops capitals too, and formal leaves your words alone. Tones apply to English.
Cleanup you choose
Light, the default, drops English ums, repeats and false starts. Medium also edits for clarity with your notes model, on your Mac with Apple Intelligence or Ollama. None keeps every word.
Voice commands
Say comma, question mark or new paragraph as you talk. Say scratch that to delete the last sentence. Works in English.
Learns your words
Add names and terms as hints and replacements. Fix a word in History, or right after a paste, and BetterWispr learns it.
Types where you were
The text lands in the app you were using. If paste is blocked, it is copied to your clipboard so nothing is lost.
History you control
Dictations stay on your Mac with the raw and the corrected text. Use Original brings back exactly what you said, and history turns off whenever you like.
Insights
See how many words you have spoken, your pace, the words cleanup saved you, which apps you dictate into and your daily streak. All of it is counted from history on your Mac.
Updates you can trust
New versions arrive from GitHub Releases through Sparkle and install only when their EdDSA signature matches.
Free and open source
Apache 2.0 licensed. Read every line on GitHub, report an issue, or build it yourself with make dev.
From thought to text
One shortcut.
Your everyday apps.
- 01
Set up once
Install BetterWispr and follow the welcome guide through permissions and your first local speech model.
- 02
Hold and speak
Place your cursor in a text field. Hold Option + Space and say what you want to write.
- 03
Release to type
Let go to transcribe. Clean text arrives in the app you were using, in the style you set for it.
What people are saying
Your voice. In your words.
Posts and replies about BetterWispr on Hacker News and X.
GodelNumbering
Just tried it out as I was looking for something that does this exact thing well (macbook). So far I dictated about 5 different things in different contexts, it worked without a single error! Good choice to pick parakeet v3. Nice work, thanks for building it!
Ed | supersetapp.com
@edsonboldrini
I'm using this one and it's amazing
Adetola Solesi
@adetola_solesi
ok so someone made a free, open source dictation app for Mac. Hold Option and Space, talk, let go, and it types into whatever app you're in. The speech models run on your Mac, unless you plug in an API yourself. No account needed.
apparent
Interested to give this a try. I've tried Wispr Flow and found it to be quite good, but a bit pricey for my taste. I guess I assumed there were equally good models that were cheaper, and I suppose this is one of them.
予知言 Lucian
@YuzhiyanLucian
语音输入也要按月订阅，我有点受不了。 BetterWispr 是个免费的 Mac 语音输入工具。按住快捷键说话，松开，文字就填进当前输入框。 选内置模型，下载好以后可以离线转写，录音不用上传。
Sameer Vanjari
@VanjariSameer
I just read your post in the morning. and now you have the app. Amazing.
小弟调调
@jaywcjlove
BetterWispr - 免费开源、本地优先的 Wispr Flow 替代品：用 Whisper、Parakeet 和 Apple 语音在设备端听写
frenchie4111
This is awesome. I really want to get something like this integrated directly into my agent IDE.
AI 极客新闻
@aigeeknews
开源的 macOS 离线听写 BetterWispr 按住 ⌥ Space 说话，松开后文字落进当前应用，转写在本机用 Whisper、Parakeet 或 Apple 的语音识别跑。
Nikhil Bhima
@nikhilbhima
haha, product looks good btw goodluck :)
Na6z
This is pretty neat, I built something similar a couple months ago.
Rahul Karajgikar
@Road_Kill11
sick stuff man
Local by design
Your words stay
on your Mac.
Models run on your Mac. Downloads happen when you choose to install them. Your speech doesn’t need a round trip to a transcription server.
How your data is handledFrom the blog
Your voice. Your call.
There’s more than one good dictation app. Our comparisons cover local processing, offline use and writing workflows, with official sources.
BetterWispr vs Superwhisper
Local models, cloud options and configurable writing modes.
BetterWispr vs Wispr Flow
Polished writing across devices, with cloud processing.
BetterWispr vs Kivi by Sarvam
Multilingual dictation, remembered corrections and voice editing.
BetterWispr vs FluidVoice
Local speech recognition with optional AI writing enhancement.
Before you download
A few good questions.
Is BetterWispr free?
Yes. BetterWispr is free and open source under Apache 2.0, with no dictation subscription, account or API key requirement. Model files use storage on your Mac.
Which Macs does it support?
BetterWispr requires macOS 14 or later. Apple Silicon is recommended for local model inference. Model availability and performance depend on your hardware and language.
Does it work without internet?
Yes, once a compatible local model and its required assets are installed. Downloadable models need an explicit installation first. Apple on device speech also depends on supported languages and OS assets. There is no cloud transcription fallback.
How do I dictate?
Focus a text field, hold Option + Space, speak, and release to transcribe. You can switch to press to toggle or choose a different shortcut in Settings. With a Parakeet model, the capsule shows your words as you speak. The text BetterWispr pastes is the transcription of the whole recording, made when you release.
Why does it need permissions?
Microphone permission lets BetterWispr record your voice. Accessibility permission allows automatic insertion into another app. Apple speech also requires Speech Recognition permission. You control these in System Settings.
What if automatic paste does not work?
BetterWispr checks the target app before inserting text. If it cannot safely paste, retrieve the transcript from the dashboard and copy it yourself. Secure fields and some apps may block automatic insertion.
Which languages are supported?
Language support depends on the selected model. Parakeet TDT v3 covers 25 European languages, Parakeet Japanese covers Japanese, and Whisper offers broader multilingual recognition. Apple speech depends on your locale and installed assets. Filler cleanup, styles and voice commands work in English. Test your chosen model with your own speech.
Does it rewrite everything I say?
Only as much as you choose. Auto cleanup starts at Light, which removes English filler words, repeats and false starts. Choose None to keep every word, or Medium to also edit English for clarity with the notes model you chose in Models. Apple Intelligence and Ollama do that on your Mac. Claude Code, Codex and API connections send the dictation to that provider, and only if you pick one. Styles adjust punctuation and capitalization for each kind of app. History keeps the raw transcript, and Use Original restores it.
Can it take meeting notes?
Yes. Notetaker transcribes your microphone as Me and, on macOS 14.2 or later, other apps’ audio as Them, while you write your own notes. Afterwards, Apple Intelligence on supported Macs running macOS 26 or a local Ollama model writes the summary, decisions and action items on your Mac. Claude Code, Codex and OpenAI compatible endpoints are optional and send the transcript to that provider. Without a notes model, the transcript and your notes are still saved.
Does it learn my words?
Yes. Add names and terms in Vocabulary, or fix a misheard word in History or right after it is pasted. BetterWispr adds the correction to Vocabulary and spells it your way next time. You can turn learning off in Settings.
Support the project
Free to use.
Fueled by coffee.
BetterWispr has no subscription and no account. If it saves you some typing, you can support its development with a donation of any amount.
Buy me a coffeeYour next thought, in your own words
Give your keyboard a break.
Local speech models. The apps you already use. A little more room to think.
“Just tried it out as I was looking for something that does this exact thing well (macbook). So far I dictated about 5 different things in different contexts, it worked without a single error!”
macOS 14+ · Apple Silicon recommended · No account in the app