Local dictation, end to end.
Whisperstream is a dictation toolkit for Windows and Mac. Core transcription runs on your computer, and downloadable local cleanup is available on compatible hardware. Model downloads, official-installer updates, and optional cloud, Agent Speak, or external-destination features use the internet as described in the relevant feature and privacy documentation.
Download for MacThe everyday pipeline: capture your voice, transcribe it on your computer.
Whisperstream transcribes your speech entirely on your Windows PC or Apple Silicon Mac using open-weight speech models: NVIDIA Parakeet or Qwen3 ASR depending on your language, or Cohere Transcribe when accuracy matters most. Your audio is never uploaded, streamed, or stored on a server, and you do not need an account. After the one-time model download, transcription works with no internet connection at all.
Dictation is push-to-talk by default: hold your hotkey, speak, and release, so nothing is ever listening in the background. The default is Right Shift, and you can remap it to any key from the Controls tab. Prefer hands-free? Switch to toggle mode, where one press starts recording and another stops it. No admin rights are needed to register the shortcut.
Whisperstream delivers transcribed text to the focused field by clipboard paste or optional simulated keystrokes. It works in many applications, including Outlook, Word, Slack, VS Code, browsers, and terminals, without an add-in. Application, security, privilege, administrator, and remote-session policies can still block or limit either method.
Whisperstream can keep a private history of completed dictations, so you can find a past transcript, replay saved audio, and copy the result again later. History is enabled by default, can be disabled, and is encrypted at rest on your device rather than synced by Whisperstream. Search by keyword, play saved audio beside its text, and delete records you no longer want.
Whisperstream transcribes 39 languages, including English, Spanish, French, German, Chinese, Japanese, Korean, Arabic, and Hindi. NVIDIA Parakeet covers 25 languages and Qwen3 ASR adds 14 more, including Cantonese, Indonesian, Malay, Persian, Thai, Turkish, and Vietnamese. Pick your language and Whisperstream selects the on-device model, downloading a matching model when needed.
Whisperstream can lower or mute your system volume while you dictate, so music or a video does not bleed into your recording or distract you. Choose off, reduce to 20 percent, or full mute in the Audio settings. Volume returns to its previous level the moment you release the hotkey.
Optional tools that enhance your workflow.
Whisperstream can optionally clean up your dictation: it removes filler words, fixes grammar and punctuation, and applies your spoken self-corrections (say "Friday, sorry Saturday" and it keeps just "Saturday"). Stream-1 Mini, our own on-device cleanup model, handles English chat and email. You can also use Ollama or a cloud or custom provider you configure. It is off by default, so you choose if and where to turn it on.
Each profile is its own AI prompt, and Whisperstream switches between them by detecting the focused application locally and reducing supported browser address data to a hostname. Start from the built-in modes or write your own profile with any prompt you want: terse for your terminal, polished for email, casual for chat. Route by app or website, with a default everywhere else. Custom prompts run with the Customizable local model or a provider you configure.
The Dictionary teaches Whisperstream your vocabulary. Boost names, products, and technical terms so AI cleanup spells them right, even when they sound like other words. Replace entries always swap one wording for another, and Filters remove words you never want typed. Import a whole list from a CSV file. Boost works with AI cleanup, including Stream-1 Mini; Replace and Filter apply to every dictation.
Agent Speak connects Whisperstream to Claude Code and Codex on your computer. When an agent finishes, Whisperstream shows a short summary, reads it aloud with an on-device voice, or opens the full response. Reply by dictating with your usual shortcut, without hunting for the right terminal. Connecting takes one click, you can pause it anytime, and it stays off until you set it up.
Beyond the built-in modes, you can give the AI cleanup your own prompt with custom formatting or style instructions, and every enhanced transcription comes back shaped to match. Keep a formal tone, stay terse, use British spelling, format as bullet points, or follow your own house style. Your prompt runs on the Customizable local model or a provider you configure, automatically, so dictated text lands already styled the way you want.
Beyond live dictation, Whisperstream transcribes audio files you select on your device without uploading or modifying the source audio. If cloud enhancement is enabled, the resulting transcript can be sent to the provider you configured. When transcript saving is on, the finished result lands in history, ready to search, replay when audio was saved, and copy.
What Whisperstream runs on, and why the install is one you can trust.
Download your speech and local cleanup models once. After that, Whisperstream can record, transcribe and clean up your text without a connection.
The Whisperstream installer is code-signed with a Microsoft-trusted Authenticode certificate under the publisher name Lanreal Technologies Inc. The signature confirms the download came from us and was not tampered with.
Lockdown Mode hardens Whisperstream for high-sensitivity work. Transcription stays on your computer, AI cleanup is limited to an on-device model, cloud cleanup is turned off and Agent Speak is suspended. History can be encrypted behind a password, with a content-free local log of access. On managed Windows devices, IT can enforce it as Managed Lockdown.
Core transcription runs on the computer you already have, so you do not need a dedicated graphics card. A modern Windows processor or any Apple Silicon Mac delivers near-instant results. Optional local AI cleanup with Stream-1 Mini runs on computers with 4 GB of memory or more.
Open source, so you can read every line of code.