Type at the speed of speech.
Press a hotkey and talk. Your words land at the cursor, 4× faster than typing.
Windows 11 · x64 & arm64
- AI enhancement built in
- No account, no subscription
- Private by default
- Try free for 7 days
Stay in the flow of your thoughts.
Press your and talk.
Press the hotkey to dictate. Right Alt by default (Right Ctrl on keyboards with AltGr), and customizable. Tap once to keep listening, or hold while you talk.
Microsoft 365 Copilot, Microsoft Teams and Visual Studio Code screenshots used with permission from Microsoft.
Demonstration: press the key and talk; the recorder listens, then the sentence appears at the cursor in Microsoft 365 Copilot, in Microsoft Teams, or in the Copilot agent prompt in Visual Studio Code.
Works with any app.
Keep your hands on your coffee. Not your keyboard.
Word
Outlook
Gmail
Teams
Slack
WhatsApp
Telegram
Discord
LinkedIn
Chrome
Notion
Obsidian
Jira
VS Code
Cursor
Claude Code
ChatGPT
And any other app: if you can type there, you can talk there.
AI enhancement. By app, or on demand. Built in
The same dictation arrives as an email in Outlook, a chat message in Slack, Chinese in WeChat.
You said
hey sarah um the login page in ember lane is broken on mobile uh the button overlaps the footer can you fix it before um tomorrow’s demo thanks
Filler words removed. Names from your dictionary corrected.
Rewritten text
Hi Sarah, The login page in Emberlane is broken on mobile: the button overlaps the footer. Can you fix it before tomorrow’s demo? Thanks!
Rewritten on your PC by a built-in AI model.
Customizable. Also on demand, by hotkey or trigger word.
You can also use your own AI server or a cloud key. Which cloud providers are supported?
Private by default.
By default, dictation and AI enhancement run on your PC. Recordings and history stay on your disk: there is no account, and no VoiceWink server ever holds them. Cloud features run only with your own API keys, and only with the providers you picked.
- Audio & history
- On your PC only
- API keys
- Encrypted by Windows
- Crash reports
- Opt-in · scrubbed
- Account
- None needed
- Goes online for
- License · updates · models
- Source
- Open source
What users say.
Malcolm Berger
“Since I started using VoiceWink, it’s saved me many hours of typing. I can now voice-type at around 200 words per minute, and the accuracy is extremely impressive. The downloadable local AI engine option is also really fast and means I don’t need a subscription to any external AI service. Feature-rich, excellent performance … Definitely worth the money.”
Tian Tian
“I often don’t realize how much I depend on something until it’s suddenly gone. VoiceWink is exactly that kind of thing — once I tried it, I never wanted to type again.”
人往往意识不到自己有多依赖某样东西，直到它突然消失。VoiceWink 就是这样的存在——用过几次之后，就再也不想打字了
Supports 100 languages.
HalloDutch
BonjourFrench
HalloGerman
HolaSpanish
CiaoItalian
OláPortuguese
CześćPolish
HejSwedish
MerhabaTurkish
こんにちはJapanese
안녕하세요Korean
你好Chinese
नमस्तेHindi
ПривітUkrainian
مرحباArabic
Γεια σουGreek
Xin chàoVietnamese
ПриветRussian
HejDanish
HeiNorwegian
MoiFinnish
AhojCzech
SziaHungarian
SalutRomanian
ЗдравейBulgarian
สวัสดีThai
HaloIndonesian
שלוםHebrew
LabasLithuanian
SveikiLatvian
TereEstonian
নমস্কারBengali
HelloEnglish
Voice-to-image. Your API key
Describe the image you want. VoiceWink generates it and copies it to your clipboard.
“isometric 3D render of a tiny data center, soft pastels, for the blog”
Optional, with your own API key. Which cloud providers are supported?
A tour of the app.
Status at a glance.
Your recording state and last transcription.
Dark theme shown. A light theme is included.
Pay once. Keep it.
Download and try everything free for 7 days.
Coming from the app? Pick a tier below.
- Same features in every tier
- Updates free when released
- 30-day money-back guarantee
* Prices in USD, VAT included, billed in USD at checkout. The euro figures are approximate and depend on your bank’s exchange rate.
Checkout by Lemon Squeezy. Your license key arrives by email; enter it in the app.
Included in every license
- Built-in AI transcription
- Built-in AI enhancement
- Cloud transcription*
- Cloud AI enhancement*
- App Mode & trigger words
- Dictionary & history
- Audio file transcription
- Voice-to-image*
* Optional cloud features: bring your own API key.
What’s built in, and what’s optional.
Dictation and AI enhancement are built in and run on your PC. The optional cloud features use your own API key.
| Feature | Built in · no usage cost | Optional · your own API key, at the provider’s prices |
|---|---|---|
| Speech transcription | Parakeet or WhisperParakeet: 25 European languages, detected automatically. Whisper: 100 languages; pin one or auto-detect. | 4 cloud providersGroq, Deepgram, ElevenLabs or OpenAI. |
| AI enhancement | Qwen3.5 or Gemma 4Four sizes that run offline. The app marks the one that suits your PC. | 7 cloud providersAnthropic, OpenAI, Gemini, Groq, Mistral, OpenRouter or Cerebras. Or your own AI server. |
| Voice-to-image | Not built in | 3 cloud providersOpenAI, Gemini or OpenRouter. |
Cloud providers: free tiers and pricesSeveral have a free tier that is generous for dictation. Checked on 4 October 2026.
Green: free for everyday use, within each provider’s limits.
| Provider | Speech transcription | AI enhancement | Voice-to-image |
|---|---|---|---|
 Anthropic
Pricing |
Not available in VoiceWink | Small free creditfor new users | Not available in VoiceWink |
 Cerebras
Rate limits |
Not available in VoiceWink | $5 free creditfor 30 days, after adding a payment method | Not available in VoiceWink |
 Deepgram
Pricing |
Free for everyday use. $200 free creditone-time · about 700 hours | Not available in VoiceWink | Not available in VoiceWink |
 ElevenLabs
Pricing |
Free for everyday use. 4.5 free hours a monththen $0.22 an hour | Not available in VoiceWink | Not available in VoiceWink |
 Gemini
Pricing |
Not available in VoiceWink | Free for everyday use. Free tierfor some models | Pay as you gono free tier for images |
 Groq
Rate limits |
Free for everyday use. Up to 2,000 free requests a dayaudio and per-minute limits also apply | Free for everyday use. Up to 1,000 free requests a daylimits vary by model | Not available in VoiceWink |
 Mistral
Pricing |
Not available in VoiceWink | Free planincludes Mistral Studio; limits not listed | Not available in VoiceWink |
| OpenAI
PricingRate limits |
$0.18–0.36 an hourno free tier | Pay as you gono free tier | Pay as you gono free tier |
 OpenRouter
Pricing |
Not available in VoiceWink | Free for everyday use. 25+ free modelsup to 50 requests a day | Pay as you gothe price depends on the model |
These are the providers’ offers, not ours; free tiers change, so confirm with each provider.
Frequently asked questions.
Does it work offline?
Yes. Dictation and AI enhancement work without internet. A paid license checks in online at least once every 30 days. Cloud transcription, cloud AI enhancement and voice-to-image need internet. More: what runs on your PC, and what still goes online.
Where does my data live?
On your PC, in %LOCALAPPDATA%\VoiceWink. Uninstalling leaves it there; you can erase it in the app or delete the folder.
What are the requirements?
- Your PCWindows 11 (x64 or arm64). A graphics card is optional and makes it faster.
- Speech models44 MB to 0.9 GB to download, up to about 2.5 GB of memory.
- AI enhancement models1.3 to 6.7 GB to download. They need at least 16 GB of memory; the largest also need a graphics card with 8 to 10 GB of video memory.
Do I need admin rights to install?
No. It installs only for your own Windows account. Work computers may still restrict which apps you can install.
Does it work with coding agents like Claude Code?
Yes. The text lands wherever your cursor is. If you can type into it, you can talk into it.
Where does AI enhancement run?
On your PC, by default. AI enhancement is built in and works without internet. If you turn it on during setup, the app offers the model that suits your PC. You can change it later in the app, or use your own AI server or a cloud provider instead.
Do I need an API key?
No. Dictation and AI enhancement are built in. You only need an API key for the cloud features: cloud transcription, cloud AI enhancement and voice-to-image. Each provider has its own key; add only the ones you use.
Is there a free trial? What about refunds?
Yes, 7 days with every feature, from the first time you open the app. No key, no email, no credit card. Every license also has a 30-day money-back guarantee.
What happens when the trial ends?
Dictation pauses until you enter a license key. Nothing is deleted: your history, dictionary and settings stay.
Other questionsAccuracy, languages, the hotkey, cloud providers, moving a license and more
Getting started
What about Windows 10, macOS, or Linux?
Windows 11 only, for now. On a Mac, try VoiceInk, the macOS app VoiceWink is inspired by.
Is the installer safe to run?
The installer is signed by DV Studio through Microsoft Trusted Signing. VoiceWink includes automatic updates.
Is the Microsoft Store version different?
It has the same features, the same 7-day trial and the same updates. The Store copy also sends one-time install reports, described in the privacy policy. Either way, you buy the license through this site.
Dictation
Can I change the hotkey?
Yes. Pick it during setup, or change it any time under Keyboard shortcuts in Settings.
Which built-in speech engine should I pick?
Parakeet. If it doesn’t cover your language, use a Whisper model. The app warns you when a model can’t handle your language and suggests one that can.
How much faster is dictation than typing?
The 4× figure is based on typing at around 40 words a minute, which is typical. If you type faster than that, the gain is smaller. If you type slower, it is bigger.
How accurate is the transcription?
Very good, not perfect. Names and jargon can be added to the dictionary for better results. Accuracy depends on the model, and newer models keep getting better. Always check the text before sending anything important.
Does it work in other languages?
Yes. Whisper covers 100 languages. Parakeet is faster and covers 25 European languages. Both detect which one you speak.
Does it paste or type?
It pastes (Ctrl+V), which is faster and works in more apps. Apps running as administrator, and some locked-down apps, may need you to press Ctrl+V yourself.
Cloud & keys
What is an API key?
A kind of password from an AI company, such as OpenAI or Groq. With it, VoiceWink uses that company’s service on your own account, and any cost goes to that account. You only need one for the cloud features.
How do I get an API key?
Create a free account with the provider and copy your key from its website: OpenAI · Groq · Deepgram · ElevenLabs · Anthropic · Gemini · Mistral · OpenRouter · Cerebras. Then enter it in VoiceWink. Many have a free tier; see their pricing pages.
How does it work with API keys?
You enter your key once, and Windows keeps it encrypted. Requests go straight to the provider, which bills you at its own prices.
Which cloud providers are supported?
- Cloud transcriptionOpenAI, Groq, Deepgram and ElevenLabs.
- Cloud AI enhancementAnthropic, OpenAI, Gemini, Groq, Mistral, OpenRouter and Cerebras.
- Voice-to-imageOpenAI, Gemini and OpenRouter.
Each one uses your own key. The built-in dictation and AI enhancement need none of them.
Can I use my own AI server?
Yes, for AI enhancement. On the AI Enhancement page, choose Local server, then Ollama or OpenAI-compatible (LM Studio and others), and enter the server’s address. Your text then goes to that server. A key is only needed if the server asks for one.
Can I write my own AI enhancement prompts?
Yes. You can edit every enhancement prompt and add your own. In App Mode, you choose which enhancement each app uses automatically.
Buying
How does the 30-day money-back guarantee work?
Email support@dvstudio.app within 30 days of buying, with your order number or checkout email. No reason needed. You get your money back the way you paid, and the license key stops working. Read the full guarantee.
Can I move my license to a new PC?
Yes. Deactivate the old machine in the app, then activate the new one. Tiers count active PCs, not lifetime installs. If the old PC is dead or wiped, support can free the slot.
It’s open source, so what am I paying for?
Convenience. You get a ready-to-install app, signed by DV Studio, that updates itself. The full source is public under GPL v3, because VoiceWink is a derivative of VoiceInk. Building it yourself is free, but takes developer tools, and you handle updates yourself. Buying a license also supports the solo developer behind VoiceWink.
More questions? support@dvstudio.app
Start typing at the speed of speech.
Try free for 7 days. No credit card needed.
Windows 11 · x64 & arm64
The Microsoft Store version has the same features, trial and updates. The license is bought through this site either way.