Speech-to-text tools for accessibility
When typing is a barrier, your voice keeps you writing.
Write hands-free in the email, document, chat or form already open. Choose Cloud for speed, or local speech-to-text for device-only and offline work.
Open source · 80,000+ downloads
When typing takes too much
The words are there. The keyboard is the barrier.
You need a way to get text into the app in front of you, without turning every correction into more keyboard work.
Every correction asks more of your hands.
When typing is painful or difficult, a transcript full of avoidable mistakes creates the same barrier twice. Use a custom dictionary for the names, acronyms and words you say often.
A hold-to-talk key is not right for everyone.
Choose toggle mode when holding a hotkey is uncomfortable. Start dictation with one press, speak, then stop when you are ready.
Your tools should not require a new workflow.
Put text into an email, document, chat or form where you can paste text. OpenWhispr uses the current writable cursor when automatic paste is available.
Internet access is not always available.
Choose a local model when you need device-only processing or an offline path. The transcription stays on your computer.
What changes
Speak the sentence. Get the text where you need it.
Choose Cloud without a local model download, or a local model for device-only processing and offline work.
Cloud transcription without a model download
Choose Cloud without downloading a local model. Audio is sent only to transcribe it, then immediately discarded.
Local transcription for offline and sensitive work
Download a local model once and dictate without an internet connection. The audio stays on your device while it is transcribed.
Text in the app already open
Press your hotkey, speak naturally, and paste the result into your document, message, email or web form.
Offline speech-to-text
Local
runs on your device without an internet connection
Cost for local speech-to-text
$0
unlimited local AI models on every plan
Free Cloud allowance
2,000
words each week on the Free plan
How it works
Get the words out without returning to the keyboard.
Start free. Pick Cloud without a model download, or local for device-only and offline dictation.
Download for free.
Install OpenWhispr on Mac, Windows or Linux. Choose Cloud or download a local model.
Dictate the thought.
Use push-to-talk or toggle mode. Speak while the writable field you want to fill is active.
Review and paste.
Check the text, then put it into your email, document, message or form.
The practical reasons
10 reasons to choose OpenWhispr for accessibility
Compare modes, input controls, language support and plans before you choose a speech-to-text tool.
Toggle mode is available
Start and stop dictation with separate presses when holding a hotkey is uncomfortable.
Local models are unlimited and free
Every plan includes unlimited local AI models, so local speech-to-text has no per-minute bill.
It works offline
Local transcription runs on your device without an internet connection.
Cloud is a quick option
Cloud works without a local model download, then immediately discards transcription audio.
Dictate into the current app
Put speech-to-text into an email, document, chat, form or any other place you can paste.
Use your own words
Add names, acronyms and recurring terms to the custom dictionary.
100+ languages
Speech-to-text supports more than 100 languages across every plan.
Open source
The MIT-licensed source is available to inspect and contribute to on GitHub.
Choose the input rhythm
Use push-to-talk for short bursts or toggle mode for longer dictation.
Start without a subscription
Free includes local models, a Cloud allowance and community support.
Before you download
Questions people ask before switching to voice input.
Straight answers on modes, cost and the day-to-day workflow.
Can I use this when typing is painful or difficult?
Should I use Cloud or a local model?
Will it work without internet access?
Can it handle names and specialised words?
Does it only make a transcript?
What does Free include, and why upgrade?
What users say
The result people notice: less typing.
Three verbatim notes from people using OpenWhispr.
$0
For unlimited local models
Local speech-to-text is included on every plan. Choose paid plans for unlimited Cloud and additional workflow features.
Started using OpenWhispr with my local models and hardware. I have to say, this is better than typing.
I switched to voice input for my Claude Code chats. Even when I stumble and rephrase mid-sentence, the transcription comes out clean and polished.
I needed a local model for when I'm travelling or have no WiFi, and this perfectly solves it. The UI and performance are great.
Pricing
Start for free.
Upgrade when you want more.
FreePopular $0No card details needed | Pro $6.67/每位使用者/月$80/用戶按年計費 Start with Pro | Business $13.33/每位使用者/月$160/用戶按年計費 Start with Business | |
|---|---|---|---|
| Best for | People who want unlimited local speech-to-text and a practical Cloud allowance | People who want unlimited Cloud transcription plus mobile, sync, and API/MCP access | People who need unlimited meetings, Agent mode, and chat over data |
| Main reason to choose | Unlimited local models, plus limited Cloud speech-to-text | Unlimited Cloud transcription plus mobile, sync, and API/MCP access | Unlimited meetings plus Agent mode and chat over data |
| Offline speech-to-textOffline speech-to-text runs entirely on your device. It works without an internet connection and is unlimited and free. | Included | Included | Included |
| Cloud speech-to-textCloud speech-to-text sends audio to OpenWhispr Cloud for the highest accuracy and speed, with no local models to download. | 2,000 words/weekvia OpenWhispr Cloud, or unlimited using your own API keys | UnlimitedOpenWhispr Cloud speech-to-text | UnlimitedOpenWhispr Cloud speech-to-text |
| Meeting recordings | 5 hours/month | 20 hours/month | Unlimited |
| Privacy & data handling | Offline audio stays on your device. Cloud audio is sent only to transcribe it, then never stored. | Offline audio stays on your device. Cloud audio is sent only to transcribe it, then never stored. | Offline audio stays on your device. Cloud audio is sent only to transcribe it, then never stored. |
| Setup experience | Hands-on: install app, choose local models, optionally add API keys | Easy: install app, upgrade, use unlimited cloud speech-to-text | Moderate: configure users, Agent mode, and data workflows |
| Advanced features |
|
|
|
| Team management | None | None | Basic team / workflow use |
| Support | Community support | Email support | Priority support |
Need SSO, compliance features, admin controls, or dedicated support for a larger team?
Enterprise includes team features and admin, SSO, SAML, SCIM, audit logs, retention controls and dedicated support.
Talk to us
Built in the open
Speech-to-text should fit the way you work.
OpenWhispr is built for the moment when the keyboard is the hard part, not the thought. Speak naturally, review the text, and keep working in the app already open.
OpenWhispr is open source. You can inspect the code yourself. Local transcription stays on your device while it is transcribed.
And if anything breaks, you talk to the people who built it, in Discord.
Free · open source · local-first
Use your voice for the words that still need to be written.
Download OpenWhispr, choose the mode that fits the moment, then use speech-to-text in the field you need to fill.
正在加載...Unlimited local AI models are included on Mac, Windows and Linux.
- Written by
- Joshua Padoa
- Reviewed and fact checked by
- Wesley van der Hoop
- Last reviewed
Drafted with AI assistance