Privacy Policy

Account & billing

When you create an OpenWhispr account, we collect the minimum needed to manage it:

• Email/password sign-up: email, name, and a hashed password (we never store your password in plain text)
• Google sign-in: email, name, and basic profile from Google. We never receive your Google password.
• Paid plans: billing details processed by Stripe. We store your customer ID and subscription state, never your full card number.
• Session cookies for authentication and automatic session refresh

Voice, audio, and transcriptions

OpenWhispr offers three transcription modes. You pick the one that fits your needs and you can change at any time in settings.

• Local processing (default). OpenWhispr can run speech-to-text fully on your device using local open-source models. When you choose this mode, no audio is transmitted anywhere.
• Bring your own API key.If you provide your own API key for a third-party transcription provider, your audio is sent directly to that provider for processing under your account. Their privacy policy applies. We don't see, store, or proxy that audio.
• OpenWhispr Cloud. Our managed transcription service. Audio is sent to our API, processed in real time, and discarded. Neither we nor any provider behind our API trains on your data. See our Security page for the current provider list and training opt-outs.

Audio Retention (Optional, off by default). If you enable this in Settings, recorded audio is saved to your device for up to 30 days so you can review or re-process it. You set the retention period; OpenWhispr deletes files automatically once they pass it. Audio Retention is local-only and is never synced to OpenWhispr Cloud or any third party.

Transcribed text is stored in a local SQLite database on your device. Transcriptions are not synced to OpenWhispr Cloud — only notes and agent conversations sync (see below).

Custom dictionary.If you add words or phrases (technical terms, names, jargon) to improve transcription accuracy, they're stored locally and passed to your transcription provider as a hint. They're not used for anything else.

Notes and AI agent conversations

Notes are stored on your device in a local SQLite database. A note can contain a title, body content, AI-enhanced versions (if you use the enhancement feature), and — for meeting notes — the meeting transcript and participant list pulled from your calendar invite.

Cloud sync (Optional).If you enable sync, your notes and agent conversation history are stored in our cloud database (Neon, encrypted at rest) so you can access them across devices. Raw audio and transcriptions don't sync — only notes and conversations do. You can disable sync at any time.

The AI Agent (Optional).When you address the AI agent by name, your prompt and any tool results (notes it reads, calendar events it queries, web searches, clipboard contents you ask it to handle) are sent to whichever AI provider you've configured. If you choose to run the agent against a local model on your own device, your prompts and any retrieved context never leave your machine.

Local semantic search. Notes are automatically indexed for semantic search using a small embedding model that runs entirely on your device. The embeddings never leave your machine.

Google Calendar (Optional)

Connecting Google Calendar is optional. If you do, OpenWhispr reads your calendar list and upcoming events (read-only — we never create, edit, or delete anything) and uses that data to:

• Notify you when a scheduled meeting is about to start
• Suggest a title for your meeting note based on the event name
• Attach the calendar invite participants to that note

Upcoming events are cached locally alongside your notes and transcriptions. This data stays on your device — we don't send it to our servers, share it, or use it for ads or AI training.

Disconnect from OpenWhispr settings to delete the local cache, or revoke access anytime via your Google Account permissions.

Limited Use.OpenWhispr's use and transfer of information received from Google APIs to any other app adheres to the Google API Services User Data Policy, including the Limited Use requirements.

Meeting detection signals

OpenWhispr can detect when a meeting is happening so it can offer to take a note. To do this it monitors two things on your device only:

• Whether known meeting apps (Zoom, Teams, Webex, FaceTime) are running on your computer
• Whether any application is currently using your microphone (on macOS, Windows, and Linux)

OpenWhispr does not capture what those other apps are doing, what they're recording, or who's on the call. It only knows the binary fact that "a meeting app is open" or "the mic is in use." These signals are held in memory only, never written to disk, never sent anywhere. You can disable meeting detection in Settings.

System audio capture (macOS 14.2+, Optional).On recent versions of macOS, OpenWhispr can record both your microphone and the audio coming from other apps so it can transcribe both sides of a meeting. This requires you to explicitly grant macOS's "System Audio Recording" permission. The captured audio is treated exactly like microphone audio: processed in real time and discarded unless you have Audio Retention enabled. This feature is macOS-only today.

Accessibility-based features

The first time you use OpenWhispr to paste a transcription, it asks for your operating system's accessibility permission. We use this for two things:

• Auto-paste:pastes your transcribed text into whatever text field you have focused, so you don't have to copy and paste manually.
• Correction learning: for up to 30 seconds after a paste, OpenWhispr watches the focused text field for edits you make to the text it pasted. If you fix a misspelled word, OpenWhispr learns the correction so future transcriptions are more accurate. The captured edits stay on your device and are never sent to OpenWhispr or any third party.

You can revoke accessibility permission in your OS settings at any time, which disables both features.

Diagnostic & technical data (Optional)

Diagnostic reporting is off by default. If you opt in, we collect anonymous performance metrics to help us improve quality and reliability:

• Audio processing metrics (duration, format)
• Speech-to-text metrics (provider, model, processing time, word count)
• LLM processing metrics (provider, model, token counts)
• Round-trip timing and error information
• Client information (client type, version, app version)

Diagnostic data may be submitted anonymously without any user or session identifier attached. It is used solely to improve performance and reliability, and is never sold or shared. You can opt out at any time in your application settings.

Referral program (Optional)

If you participate in the referral program, we collect:

• Your unique referral code and the invitations you send
• The email addresses of people you invite (uploaded to our servers so we can track conversions and prevent abuse)
• Click analytics on your referral link (user agent, referring URL)
• Whether a referral results in a sign-up or subscription

We only email a recipient when you initiate the invite. Referral data is used to attribute rewards and prevent abuse — nothing else.