Audience
Privacy-conscious professionals for whom cloud dictation is a deal-breaker, and AI-focused individuals who want to work faster by speaking rather than typing prompts.
About Whisperstream
Whisperstream is a desktop dictation app for Windows PCs and Apple silicon Macs (beta) that converts speech into text for the focused field in other applications using a push-to-talk shortcut. After its speech-recognition models are downloaded, dictation can run locally and offline. Available models include NVIDIA Parakeet, Qwen3 ASR and Cohere Transcribe. Optional cleanup uses the on-device Stream-1 Mini model or a provider configured by the user. Features include custom vocabulary and text replacements, app-specific enhancement profiles, searchable transcript history, audio-file transcription, and voice playback and replies for Claude Code and Codex sessions. It supports dictation into compatible text fields without an add-in and is designed for people who want to speak into coding editors, email, documents and other applications. Model downloads, software updates and optional online functions may require internet access.
Pricing
Integrations
Company Information
Videos and Screen Captures
Whisperstream desktop settings screen with transcription metrics, dictation language, voice model, and privacy controls.
