# Whisperstream

Whisperstream is a Windows dictation app from Lanreal Technologies Inc. It records from a selected microphone, recognizes speech on the user's PC, and inserts the completed text into the app the user is working in. Optional AI enhancement is off by default and can run locally or through a provider the user configures.

Whisperstream costs $29 USD for 1 device or $49 USD for up to 2 devices as a one-time purchase with no subscription.

## Key facts

- Platform: Windows 10 or Windows 11, x64
- Pricing: $29 USD for 1 device or $49 USD for up to 2 devices, one-time purchase
- Trial: 7 calendar days starting with the first dictation that produces text
- Trial signup: No account or credit card required
- Publisher: Lanreal Technologies Inc., Toronto, Canada
- Product: https://whisperstream.io
- Documentation: https://whisperstream.io/docs
- Support: support@whisperstream.io

## Product documentation

### Getting started

- Install and configure: https://whisperstream.io/docs
  Install Whisperstream, complete first-run setup, and make a first dictation.
- App basics, licensing, updates, and uninstall: https://whisperstream.io/docs/getting-started/app-basics
  Use the notification-area app, configure startup and theme, manage the trial or Pro license, install updates, get help, and uninstall.

### Dictation

- Recording controls: https://whisperstream.io/docs/dictation/recording-controls
  Configure Push to Talk, Toggle, the recording indicator, and shortcuts that reuse the most recent dictation.
- Languages and speech recognition models: https://whisperstream.io/docs/dictation/languages-models
  Choose one of 39 dictation languages. Automatic selection uses Parakeet or Qwen3 ASR; Manual selection also offers Cohere Transcribe for its 14 supported languages.
- Audio: https://whisperstream.io/docs/dictation/audio
  Choose a microphone, configure recording chimes, and leave, lower, or mute Windows audio while recording.
- Live Preview: https://whisperstream.io/docs/dictation/live-preview
  View provisional words in the recording indicator and understand how they differ from completed text.
- Text insertion: https://whisperstream.io/docs/dictation/text-insertion
  Choose Clipboard or Keystroke delivery and test accessibility, remote-session, game, and elevated-app compatibility.
- Dictionary: https://whisperstream.io/docs/dictation/dictionary
  Filter unwanted words and replace recurring recognized terms in completed dictation.

### AI enhancement

- Enhancement providers: https://whisperstream.io/docs/enhancement/providers
  Choose Local (powered by Gemma 4 E2B), Ollama, Gemini, OpenAI, Anthropic, or a Custom service. Cloud model choices include a Recommended option and support custom model names; list refreshes preserve saved selections.
- Profiles and routing: https://whisperstream.io/docs/enhancement/profiles-routing
  Use built-in or custom cleanup profiles and select them manually, by website, by application, or as a default.

### Data and privacy

- Transcript history: https://whisperstream.io/docs/data/transcript-history
  Control saved transcript and audio history, retention, search, playback, copying, import, and deletion.
- Lockdown Mode: https://whisperstream.io/docs/data/lockdown-mode
  Enable password-gated history controls, limit enhancement to Local, manage automatic locking and recovery, or turn Lockdown off.

### Workflows and integrations

- Pin Mode: https://whisperstream.io/docs/workflows/pin-mode
  Send dictation to one selected Windows target while working in another window.
- Agent Speak: https://whisperstream.io/docs/workflows/agent-speak
  Connect Codex or Claude Code, independently enable written summaries or local speech, and dictate replies through the HUD.

### Reference and support

- Settings and data locations: https://whisperstream.io/docs/reference/settings-data-locations
  Find settings and local data, move downloaded models, export logs, and choose what survives uninstall.

## Canonical pages

- Home: https://whisperstream.io/
- Features: https://whisperstream.io/features
- Documentation: https://whisperstream.io/docs
- About: https://whisperstream.io/about
- End User License Agreement: https://whisperstream.io/eula
- Privacy Policy: https://whisperstream.io/privacy
- Website Privacy Policy: https://whisperstream.io/privacy-website
- Service-provider list: https://whisperstream.io/subprocessors
- Terms of Service: https://whisperstream.io/terms

## Publisher

- Legal name: Lanreal Technologies Inc.
- Location: Toronto, Ontario, Canada
- Product support: support@whisperstream.io
- General contact: contact@lanreal.io
- Company website: https://www.lanreal.io/
- GitHub organization: https://github.com/lanreal-io