# Whisperstream Whisperstream is private local dictation software for Windows. It captures your voice with a push-to-talk hotkey, transcribes it entirely on your PC using a local AI model, and types the result into whatever app you have focused. Your audio never leaves your machine. An optional AI cleanup step (off by default) can polish filler words and formatting using a local model on a capable GPU, with a free cloud fallback otherwise. One-time purchase at $29 USD, no subscription. ## Key facts - Platform: Windows 10, Windows 11 (64-bit) - Pricing: $29 USD, one-time purchase, no subscription - Pricing details (machine-readable): [pricing.md](https://whisperstream.io/pricing.md) - Free trial: 10 minutes of transcription, no account or credit card required - Publisher: Lanreal Technologies Inc., Toronto, Canada - Product page: [whisperstream.io](https://whisperstream.io) - Support: [support@whisperstream.io](mailto:support@whisperstream.io) - Publisher contact: [contact@lanreal.io](mailto:contact@lanreal.io) - GitHub org: [github.com/lanreal-io](https://github.com/lanreal-io) - Parent company: [lanreal.io](https://www.lanreal.io/) ## Features Full feature page: [whisperstream.io/features](https://whisperstream.io/features) - On-device transcription: All transcription happens locally on your CPU using NVIDIA's open-weight Parakeet TDT v3 model. Your audio never leaves your machine and no account is required. - Push-to-talk hotkey: Hold a hotkey to dictate, release to stop. Default is Right Shift, remappable to any key; a toggle mode is also available. No admin rights needed. - Types into any app: Pastes transcribed text into whatever window has focus. Works in Outlook, Word, Slack, VS Code, browsers, and terminals with no add-in or per-app setup. - Transcript history: Keeps a private, searchable history of everything you dictate, with audio playback. Encrypted at rest on your device and never synced to a server; search, replay, and delete entries locally. - Audio file import: Transcribes audio files you already have (meetings, voice memos, interviews) through the same on-device Parakeet model, with no upload or account. Imported transcripts land in your history. - Optional AI cleanup: Off by default. Removes filler words, fixes grammar and punctuation, and applies spoken self-corrections. Runs locally on a capable GPU, with a free cloud fallback for older hardware, and also works with any OpenAI-compatible provider. - Automatic profile switching: Gives each app or website its own AI prompt and applies it automatically by detecting the focused window. Start from the built-in modes or write your own profile with any prompt; route by app or by a specific site, with a default everywhere else. - Custom dictionary: Word-for-word overrides so names, technical terms, and acronyms are spelled the way you want. Case-insensitive and applied to every transcription. - 39 languages: Transcribes 39 languages (the 25 European languages it already covered, plus 14 more such as Chinese, Japanese, Korean, Arabic, Hindi, and Vietnamese) on-device, with no per-language download. - Works offline: Needs the internet only to download the model and activate the license once. After that, dictation, transcription, and formatting run with no connection. - Microsoft-signed installer: Code-signed with a Microsoft-trusted certificate, so Windows shows a verified publisher instead of an unknown one. - Custom style prompt: Give the AI cleanup your own prompt with custom formatting or style instructions (tone, terseness, spelling, bullet formatting, house style), and every enhanced transcription comes back shaped to match. It runs on a local model or any OpenAI-compatible provider. - System-volume ducking: Optionally lowers (to 20 percent) or mutes system volume while you dictate, then restores it on release. - Runs on CPU, no GPU required: Core transcription runs on a normal processor; a GPU is only used for the optional AI cleanup. Works on 8 GB of RAM, 16 GB recommended. ## Canonical pages - [Home](https://whisperstream.io/) - [Features](https://whisperstream.io/features) - [About](https://whisperstream.io/about) - [End User License Agreement (EULA)](https://whisperstream.io/eula) - [Privacy Policy](https://whisperstream.io/privacy) - [Website Privacy Policy](https://whisperstream.io/privacy-website) - [Subprocessors](https://whisperstream.io/subprocessors) - [Terms of Service](https://whisperstream.io/terms) ## Comparisons and alternatives - [Whisperstream vs Wispr Flow](https://whisperstream.io/vs/wispr-flow): Side-by-side comparison of Whisperstream and Wispr Flow on price, privacy, and Windows performance, with a 5-step switching guide. - [Whisperstream vs Windows Voice Typing (Win+H)](https://whisperstream.io/vs/windows-voice-typing): Side-by-side comparison of Whisperstream and the built-in Windows Voice Typing (Win+H) on price, privacy, reliability, and cloud-vs-on-device behavior. - [Whisperstream vs Willow Voice](https://whisperstream.io/vs/willow-voice): Whisperstream vs Willow Voice on price ($29 once vs $144/year), privacy, and AI rewriting; Whisperstream adds optional on-device AI cleanup. - [Whisperstream vs Aqua Voice](https://whisperstream.io/vs/aqua-voice): Whisperstream vs Aqua Voice on price, privacy, and a controlled word-error-rate benchmark; literal on-device transcription with optional local AI cleanup vs Aqua's always-on Avalon rewriting. - [Whisperstream vs OpenWhispr](https://whisperstream.io/vs/openwhispr): A focused paid Windows app with no cloud transcription path vs an open-source app offering three transcription modes. - [Wispr Flow alternatives for Windows](https://whisperstream.io/alternatives/wispr-flow): Six Wispr Flow alternatives for Windows in 2026 (local, cloud, free, and paid), ranked by privacy and price. - [MacWhisper for Windows](https://whisperstream.io/macwhisper-for-windows): MacWhisper is a Mac-only transcription app; Whisperstream is the Windows-native pick for on-device dictation and audio-file transcription ($29 once, NVIDIA Parakeet V3 on CPU). MacWhisper still goes further with speaker labels and subtitle and document export. - [VoiceInk for Windows](https://whisperstream.io/voiceink-for-windows): VoiceInk is a Mac-only, open-source dictation app. Whisperstream is the Windows-native option running the same NVIDIA Parakeet model, $29 once with two activations, fully local. - [Superwhisper alternatives for Windows](https://whisperstream.io/alternatives/superwhisper): Five Superwhisper alternatives for Windows in 2026, ranked for a Superwhisper user, with Whisperstream as the $29 one-time local pick. - [Dragon NaturallySpeaking alternatives for Windows](https://whisperstream.io/alternatives/dragon-naturallyspeaking): Five Dragon NaturallySpeaking alternatives for Windows in 2026 (local, cloud, free, and paid), ranked for a Dragon refugee. - [Best dictation software for Windows](https://whisperstream.io/best-dictation-software-windows): The best dictation software for Windows in 2026, seven picks ranked by privacy and one-time price. - [Dictation software that works with screen readers on Windows](https://whisperstream.io/screen-reader-dictation-windows): Windows dictation apps tested with NVDA, JAWS, and Narrator, on two axes (does the hotkey fire, and does the text land). Several work; Superwhisper failed all three and Aqua Voice's default hotkey does not work with Narrator. ## Troubleshooting - [Win+H not working: Microsoft-documented fixes](https://whisperstream.io/win-h-not-working): Seven Microsoft-documented fixes for Windows 11 Voice Typing (Win+H), in the order to try them, including the managed-org speech policy fix Microsoft's troubleshooter never mentions. Closes with the local-alternative pitch for Whisperstream. ## Guides - [Dictation for Citrix and RDP](https://whisperstream.io/dictation-for-citrix-and-rdp): Clipboard-based dictation breaks inside Citrix, RDP, and Azure Virtual Desktop when administrators restrict clipboard redirection (off by default on new Azure Virtual Desktop and Windows 365 deployments). Whisperstream's keystroke input mode types dictation in as keyboard input, the channel a remote session always accepts, with no IT-deployed extension. Contrasts the keystroke, clipboard-paste, and native virtual-channel (Dragon) approaches.