Type at the speed of speech.
Hold a hotkey and talk — your words land at the cursor in any Windows app, 4× faster than typing.
RE: Q3 delivery — email
OpenAItext + image
Groqtext
Deepgramtext
ElevenLabstext
Anthropictext
Geminitext + image
Mistraltext
OpenRoutertext + image
Cerebrastext
Works with any app.
Keep your hands on your coffee. Not your keyboard.
AI enhancement. By app, or on demand.
AI enhancement rewrites your dictation before pasting it. App Mode applies the enhancement you’ve set for each app. You can also select one with a hotkey or trigger word.
hey um so basically the update is done uh can you check the link and um let tom know we're good for tomorrow
Hi, The update is complete. Could you review the link and confirm with Tom that we're set for tomorrow? Thanks!
your API keys, your provider — Anthropic, OpenAI, Gemini, Groq, Mistral, OpenRouter, Cerebras
Add names, jargon and product codes to the dictionary so they are recognized more reliably. Recognition hints depend on the transcription model. Word replacements work across models.
Every enhancement is an editable prompt. Tweak the built-ins or write your own.
Start or end what you say with a trigger word to pick an enhancement by voice.
Try it on your next email.
Try it free for 7 days. Buy a lifetime license if you want to keep using it.
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 — spoken prompt examples
listening…
Describe the image you want. VoiceWink generates it using your chosen provider and copies it to your clipboard.
A tour of the app.
Recording, in context.
A small floating window shows the recording, its length and the app the text will be pasted into.
dark theme shown — light and system included
Your voice never has to leave your machine.
Transcription runs on your PC by default, and your recordings and history stay there — no VoiceWink server holds them, and there is no account. Your voice is only transcribed; no voiceprint is created. Cloud processing happens only with your own API key, and only with the provider you chose.
Pay once. Keep it.
Lifetime licenses from $25.
Local dictation has no usage charges. Optional cloud features use your own API keys, and several providers’ free tiers are generous for dictation.
Try free for 7 days — no credit card.
Windows 11 (x64 & arm64) · GPL v3 · Lost your license key?
* Prices in USD, VAT included, billed in USD at checkout; for euro customers approx. €22 / €34 / €42, depending on your bank’s exchange rate.
Optional cloud services.
VoiceWink is bring-your-own-key: you paste your own API key, requests go straight to the provider, and the provider bills you at its own prices — VoiceWink adds nothing on top.
By default, dictation runs locally and needs no API key or account. A key adds the cloud options: dictation on the big cloud models, AI enhancement, and voice-to-image. Several providers offer a free tier. Limits and options for additional usage vary by provider.
Two local engines are available. Switch between them any time.
A balance of speed and accuracy for everyday dictation.
Models from small to large; pick one for languages Parakeet doesn’t cover.
Groq
Whisper on their free tier. Each dictation counts as one request. Their rate limits have the current figures.
Deepgram
A $200 signup credit, no card required, and it does not expire. Deepgram estimates that at about 700 hours of transcription on their Nova model, before add-on features. Rates are on their pricing page.
ElevenLabs
Scribe transcription. The free plan includes 4.5 hours of audio a month, then it is billed by the hour. Current rates are on their API pricing page.
OpenAI
No free tier; pay-as-you-go transcription costs 18 to 36 cents per hour of audio, depending on the model. Per-model prices are on their pricing page.
Checked 15 September 2026 — these are the providers' offers, not ours; free tiers change, so confirm with each provider · AI enhancement can use free tiers too. Some Groq chat models allow up to 1,000 requests a day on the free tier; limits vary by model.
Frequently Asked Questions.
Does it work offline?
Yes. Local dictation works offline once your model is downloaded. A paid licence needs to reconnect at least once every 30 days for validation. Cloud transcription, AI enhancement and voice-to-image need an internet connection.
Where does my data live?
All of it sits under %LOCALAPPDATA%\VoiceWink, on your machine. Uninstalling leaves it there — you can erase it any time from inside the app, or delete the folder yourself.
What are the requirements?
Windows 11, including ARM64 PCs through x64 emulation. No GPU required; GPU acceleration is available on supported hardware. Larger local models need more memory. The installer includes the .NET runtime.
What about Windows 10, macOS, or Linux?
Windows 11 only, at the moment. On a Mac, look at 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.
Do I need admin rights to install?
No. VoiceWink installs for your Windows user account, without admin rights. Work computers may still restrict which apps you can install.
Which local engine should I pick?
Parakeet, unless you need a language it doesn’t cover — then switch to a Whisper model. If you pick a language your model can’t handle, the app says so 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.
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 — 100 languages via the local Whisper engine (pin one or auto-detect); the faster Parakeet engine covers 25 European languages. Pick a language a model can’t handle and the app says so — and suggests one that can.
Does it paste or type?
It pastes (Ctrl+V) — faster and more compatible than simulated typing. VoiceWink pastes into apps that accept pasted text. Some restricted or administrator-run apps may require you to paste manually.
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.
Can I write my own AI prompts?
Yes. You can edit every enhancement prompt and add your own. In App Mode, you choose which enhancement each app uses automatically.
Do I need an API key?
No. Local dictation needs no API key or account. You can download local models during setup, or any time later from the Models page. API keys are only for the optional cloud features: cloud transcription, AI enhancement and voice-to-image.
How do I get an API key?
Create a free account with the provider you like and copy the key from their console: OpenAI · Groq · Deepgram · ElevenLabs · Anthropic · Gemini · Mistral · OpenRouter · Cerebras. Then paste it into VoiceWink once — done. Some providers include a free tier, some do not. Their own pricing pages have the current details.
How does bring-your-own-key work?
Paste your API key once — it's encrypted by Windows (DPAPI). Requests go straight to the provider; your account, no middleman.
Is there a free trial? What about refunds?
7-day full-featured trial — it starts inside the app the first time you run it. No key, no email, no credit card. After purchase, every tier 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 are all there when you return.
How does the 30-day money-back guarantee work?
Email support@dvstudio.app within 30 days of purchase with your order number or the email you used at checkout — no reason needed. The refund goes back to your original payment method via Lemon Squeezy, and your license key is deactivated.
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.
Why GPL v3? What am I paying for?
The full source is available under GPL v3. VoiceWink is a derivative of VoiceInk. Paying gets you signed builds, automatic updates and email support. You can compile it yourself for free.
More questions? support@dvstudio.app
Start typing at the speed of speech.
Try free for 7 days — no credit card.