VoxCast
100% local · runs offline on your GPU100% local · offline · your GPU

Speak. Don't type.

Press the hotkey, speak, and your text lands right in the active window. Speech recognition runs entirely on your machine: no cloud, no upload, no subscription.

Download free How it works
Ready

Click the mic and speak: your text appears.

100% local Free Windows 10 & 11 Hotkey Ctrl Shift Space

How it works

From thought to text, in three steps.

No setup marathon, no cloud sign-up. Install, press the hotkey, go.

Press the hotkey

Start from anywhere

Press Ctrl+Shift+Space, no matter which program is open. VoxCast listens.

Ctrl + Shift + Space
Speak

Just talk

Say what you want to write. The panel shows live that it's recording.

Text appears

Right in the window

Your spoken text lands in the active window instantly, by typing, clipboard or both.

Features

All local. All yours.

Dictate, convert, enhance. Every function runs on your hardware.

Dictation via global hotkey

One shortcut starts and stops recording. The recognized text goes straight into the active window, whether browser, mail client or editor. No window switching, no manual paste.

Record meetings

System audio plus microphone: VoxCast captures Zoom, Meet, Teams, WhatsApp and any other app, and turns it into a timestamped transcript, locally.

AI enhancement

Turn your dictation into a finished email or tidy text. Optional, with your own Anthropic or OpenAI key.

Files → Markdown

Audio and documents become clean Markdown locally, by right-click or drag-and-drop. Save location is up to you.

GPU-accelerated

The full CUDA runtime ships in the installer and runs even without an installed CUDA toolkit. No GPU? VoxCast uses the CPU.

Three accuracy tiers

Swift, Precise or Ultra: from feather-light to near-flawless, whatever your machine can handle.

Multilingual

Dictate in English, German and many more languages. VoxCast recognizes a broad range, no mental switching.

Automatic updates

VoxCast tells you when a new version is out. Nothing to check by hand.

Meetings

Every meeting becomes text.

VoxCast records the system audio and your microphone, whether it's Zoom, Google Meet, Teams, a WhatsApp call or the browser. Or record just one app: music, system sounds and everything else stay out of the transcript entirely. Even hour-long meetings end up on your disk as an audio file plus a timestamped transcript, fully local. Optionally, AI enhancement prepends a summary with decisions and action items.

Works with

ZoomGoogle MeetTeamsWhatsApp+ any app

Play fair: let participants know before you record. In many countries recording without consent is a criminal offence. VoxCast reminds you before your first recording.

Files → Markdown

Files become Markdown, locally.

Drop a file on the panel or pick „Convert to Markdown" in the right-click menu. Audio is transcribed by VoxCast on your machine, documents are read cleanly by MarkItDown. Where it's saved is up to you.

Audio

MP3OGGM4AWAVFLAC

Documents

PDFDOCXPPTXXLSXCSVDocuments
VoxCast Server

One strong PC. Transcription for the whole network.

VoxCast Server runs the speech recognition on a single machine with a strong GPU, and every VoxCast on your network uses it: dictation, meetings and file conversion. Your audio stays in the building, no cloud involved.

  1. 1Install VoxCast Server on the machine with the strong GPU. The setup registers the Windows service and opens the firewall for you.
  2. 2On any PC, open VoxCast Settings, enable the remote server and click "Find server". One click fills in the address.
  3. 3Paste the API key (Start menu: "VoxCast Server API key"), save, done. Every transcription now runs on the server.
Server for Windows Setup guide

Linux or Docker? Download the server package and follow the setup guide.

Privacy

Nothing leaves your machine.

Your recordings are processed locally, full stop. There's no upload, no cloud service and no account where your voice could end up. The speech models live on your disk, your API key for AI enhancement safely in the Windows Credential Manager. For confidential dictation that makes it the privacy-friendly, GDPR-ready choice.

  • No cloud transcriptionAudio and text stay on your hardware.
  • No account, no subscriptionSpeech recognition costs nothing.
  • This website holds to it tooNo cookies, no trackers, self-hosted fonts.
Your data

Everything local. Enhancement only if you want it.

This is how your data flows: exactly this far, and not one step further.

Orange glowing audio waveform fully enclosed in a glowing frame with a green status dot: your signal stays inside the device
Always · 100% local

Dictation, meetings, files

Recording, speech recognition and transcripts happen entirely on your GPU or CPU. None of it ever leaves your machine: no upload, no account, no cloud.

  • Works fully offline
  • Audio & text stay on your disk
  • No subscription, no hidden costs
Violet audio waveform flowing through a glowing keyhole of light: only your API key opens the way
Optional · your key only

AI enhancement

Only when you switch it on, the finished text (never your audio) is refined with your own Anthropic or OpenAI API key. You hold the key, you decide.

  • Off until you enable it
  • Only text is sent, never audio
  • Your key, safe in the Windows Credential Manager

No key, no outside connection. VoxCast still dictates, transcribes and converts at full power.

Who it's for

Made for everyone who writes a lot.

Heavy writers

Emails, notes and texts spoken faster than typed.

Developers

Dictate comments, commit messages and docs without taking your hands off the keyboard.

Journalists & authors

Turn interviews and voice memos into searchable local text.

Accessibility

Operate your computer by voice, in any program, with no cloud dependency.

Full control

Set up the way you work.

Microphone, speech model, language, output mode and hotkey: all in one place, in the same dark look as the panel. Choose between Swift, Precise and Ultra, clipboard or typing, and set your save location.

Model: Swift / Precise / Ultra Output: Clipboard / Typing / Both Language: free choice
Dark VoxCast settings window with Audio, Recognition and Output sections, with selectors and switches.
FAQ

Frequently asked.

Is VoxCast free?
Yes. VoxCast is a free download for Windows 10 and 11. There is no subscription for the speech recognition itself, it runs entirely on your machine. Only the optional AI enhancement uses an external provider and your own API key.
Does speech recognition really run offline?
Yes. Transcription happens 100% locally on your own GPU or CPU. After the models are downloaded no internet connection is needed, and no audio is uploaded to any cloud.
Which file formats are supported?
Audio as MP3, OGG, M4A, WAV and FLAC. Documents as PDF, DOCX, PPTX, XLSX, CSV and images. Everything is processed locally into clean Markdown.
Do I need a GPU?
No. VoxCast also runs on the CPU. With a compatible NVIDIA GPU recognition is much faster thanks to the bundled CUDA runtime. A separate CUDA installation is not required.
Which languages does VoxCast support?
English, German and many more. VoxCast covers around 99 languages. Speech recognition works fully offline for every supported language.
Does my audio leave the machine?
No. Recording and transcription stay fully local. Only if you enable the optional AI enhancement is the generated text sent to your chosen provider (Anthropic or OpenAI).
How does AI enhancement work?
Optional and with your own Anthropic or OpenAI API key. Your dictation is rewritten into an email, reply or tidy text. You can create your own modes; the key is stored safely in the Windows Credential Manager.
Can VoxCast transcribe meetings and video calls?
Yes. VoxCast records the system audio and optionally your microphone. This works with Zoom, Google Meet, Teams, WhatsApp Desktop and any other app, no plugins required. You can also record just a single app, keeping music and system sounds out entirely. Even multi-hour meetings are saved locally as an audio file and processed into a timestamped transcript. Important: let participants know before recording; in many countries recording without consent is a criminal offence.
What are the system requirements?
Windows 10 or 11 (64-bit). A GPU speeds up recognition but is not required. Current version: 1.9.1.

Write with your voice.

Download VoxCast and dictate into any window. Free, local, ready in minutes.

Download for Windows

Windows 10/11 · NVIDIA GPU recommended (CPU otherwise)

Choose language

DeutschEnglishEspañolFrançaisItalianoPortuguêsNederlandsPolskiTürkçeРусский中文日本語한국어

What's new

Every VoxCast release at a glance.

v1.9.1Latest

Improved

  • VoxCast keeps working when the server is not available: VoxCast now checks at every start, and regularly while it runs, whether your VoxCast Server can be reached. If it cannot, dictation, meetings and file conversion switch to this PC (GPU or CPU) automatically, and you get a notification saying so.
  • Automatic return to the server: VoxCast keeps trying the server in the background and notifies you as soon as it is reachable again, then puts the work back on the server.
  • A recording is no longer lost when the server drops out mid-dictation: the recording is transcribed on this PC instead of ending with an error.
  • Nothing in progress is interrupted: a running dictation, meeting or live session always finishes; the switch only applies to the next one.
  • Server status in the settings: the remote server section shows whether the server is reachable and where transcription is running right now.
v1.9.0

New

  • VoxCast Server, transcription for your whole network: run the new self-hostable VoxCast Server on one machine with a strong GPU and every VoxCast on your network uses it for dictation, meetings, live captions and file conversion. Your audio stays on your network, no cloud involved. Free download for Windows (Linux and Docker packages included) at getvoxcast.com/server.
  • Find your server with one click: Settings, Remote server, "Find server" lists every VoxCast Server on your network; one click fills in the address, no IP addresses to type.
  • Central AI enhancement: the server can hold one company AI key, so clients enhance dictations and meeting summaries through the server without entering a key of their own. Choose "Use the server" under AI enhancement.
  • Company AI modes: define enhancement prompts once on the server and everyone can pick them, alongside their own modes.
  • Encrypted connection (HTTPS): the server can serve HTTPS with a self-signed certificate; the client trusts it once by confirming its fingerprint, then remembers it.
  • Enterprise rollout: companies can ship VoxCast pre-configured and lock the server and key settings via a managed policy file.

Improved

  • Activation window behaves like a normal window: it can be moved (drag the title), shows a taskbar entry and no longer stays on top of every other window.
  • When a server is connected, the local model choice is disabled with a note, since recognition runs on the server.
v1.7.2

New

  • Automatic language detection for audio files: converting audio to Markdown now detects the spoken language by itself, even when it changes mid-file; before, the dictation language was forced. A new "Audio language" picker in Settings under File Conversion can still pin a language.

Fixed

  • Conversion always delivers a result: converting a file right after the app starts now waits for the speech engine instead of instantly claiming success with an empty or missing file; real problems show an honest error and no file is written.
  • Background jobs can no longer vanish: conversions, updates, activation and meeting actions are now protected against being cancelled silently by the runtime; a started conversion always ends with a file or a clear error.
  • First recording after launch: the waveform now reacts from the first second on every system; a slow one-time component load could freeze it during the very first recording.
v1.7.1

Improved

  • Model switch with confirmation: picking a model tier that is not installed yet now asks before downloading and shows the download size; the progress window no longer asks for your dictation language again.
  • Crash reports: in the rare case of a crash, VoxCast now writes a report file that makes the cause diagnosable for support.

Fixed

  • First dictation after launch: a recording started right after the app launches now begins reliably and the waveform reacts immediately; it could stay frozen for around ten seconds or the recording silently never started.
  • Stability when docked: fixed a crash that could occur when the panel was docked to a screen edge and the small panel was switched on.
  • Small panel: the AI button next to the microphone is no longer cut off.
  • Smoother waveform: the level display no longer stutters on slower machines while the speech engine is busy.
  • Microphone level: the automatic input level boost before a recording works again on all systems.
v1.7.0

New

  • Hardware check on first start: VoxCast now detects your graphics card during setup and preselects the best model tier for your PC (Ultra on capable cards). You can change it in Settings at any time.
  • Digitally signed: the app and its installers are now signed by Hashfox GmbH, so Windows can verify the publisher.
  • Much smaller updates: starting from this version, future updates download only the changed part of the app (about 200 MB) instead of the full package.
  • Movable windows: the download and update windows can now be dragged aside; they open centered again on the next start.

Improved

  • Clearer Settings: switches sit right-aligned so labels are never cut off, help texts are easier to read, and automatic language detection is now its own switch that locks the language picker while active.
  • With live transcription enabled, the text output options are greyed out and a note explains why they do not apply there.
  • The AI menu opens as a seamless extension of the panel and stays fully visible at every screen edge.
  • In the small panel, clicking the waveform stops the recording.
  • The installer now speaks 12 languages, and the Settings window gets its own taskbar button while it is open.
  • The panel shows AI enhancement in blue and previews the result in a single line.

Fixed

  • The microphone test no longer freezes the app on the first click; stopping early keeps the partial recording for playback.
  • The language list during setup is no longer cut off at the window edges.
  • English now shows its flag everywhere in the app.
v1.6.1

Improved

  • Reliable update notifications: VoxCast now keeps checking for new versions while it runs (every few hours), not just once at launch. If the check fails because your network was still waking up, it retries within a minute.
  • Checking for updates manually in Settings now also opens the update window with the full changelog.
  • The update window waits for the right moment: it never interrupts you while dictating, transcribing or recording a meeting and appears once VoxCast is idle again.
v1.6.0

New

  • Live transcription: turn it on in Settings and your words appear at the cursor while you speak, instead of after you stop. Best with a graphics card; it also runs on the processor with a heads-up that it may lag.
  • Three new AI modes: To-do list, Notes and Formal join Clean up, E-Mail and Reply. Existing installations receive them automatically.
  • 13 interface languages: the app now speaks English, German, Spanish, French, Italian, Portuguese, Dutch, Polish, Turkish, Russian, Chinese, Japanese and Korean. VoxCast follows your Windows display language automatically; you can pick one in Settings, switching applies instantly.

Improved

  • AI enhancement now reliably answers in the language you dictated: VoxCast tells the AI which language it heard instead of letting it guess. This also protects your own custom modes.
  • Smarter AI model selection: if the recommended model is not available for your API key, VoxCast automatically finds a suitable one (Anthropic and OpenAI).
  • Sharper built-in AI prompts: e-mails no longer invent names and keep the formality you dictated; all modes resolve self-corrections while speaking.
  • Built-in AI mode names now follow the interface language.

Fixed

  • Starting a dictation while VoxCast is still starting up no longer hides the waveform for that first recording.

Note

  • Live transcription types raw text at the cursor and does not use AI enhancement (that step rewrites the whole text, which streaming cannot do).
v1.5.1

New

  • Update dialog with changelog: when a new version is available, VoxCast now shows what's new and asks you to confirm before downloading and installing.

Improved

  • The update download window is clearer, with the full change list and progress.
v1.5.0

New

  • Record a single app: capture just Zoom, Teams, WhatsApp, Meet or any other app; music, notifications and other system sounds stay out of the transcript.
  • Automatic meeting language: meetings are transcribed in whatever language is spoken, and handle a language switch in the middle of a call. You can still pin a fixed language in Settings if you prefer.

Improved

  • Better microphone and headset compatibility when recording meetings.
v1.4.1

New

  • Meeting recording polished: clickable stop, notifications for every result, and clicking the "meeting transcribed" toast opens the transcript.

Fixed

  • USB headsets no longer prevent meeting recording from starting.
  • Unfinished meeting recordings (e.g. after a crash or quit) are transcribed automatically on the next start; nothing is lost.
  • Long dictations are no longer cut off when enhanced with AI; the original text is always recoverable.
v1.4.0

New

  • Record & transcribe meetings and calls: system audio plus your microphone, works with Zoom, Meet, Teams, WhatsApp and any other app. Saves an audio file and a timestamped transcript, fully local, with an optional AI summary.
  • New "Ultra" accuracy tier for the best transcription quality, and a hint in Settings showing whether a model fits your graphics card.
v1.3.5

New

  • Bilingual interface (English / German) with instant switching in Settings.
v1.3.4

Improved

  • More robust activation and updates on unstable connections.
v1.3.3

Fixed

  • Fixed the "license invalid" problem: activation, updates and AI enhancement now reliably reach the server.

Improved

  • Update check now runs before the activation screen, so a stuck activation can always be resolved by installing the newest version.

Get VoxCast for free

Leave your e-mail and get your activation key. Then you can download VoxCast for Windows.

Recover your key

Enter the email address you used to get your key. It will be shown to you again right here.

Purchased license? Email info@hashfox.com and we will help you out.