Privacy Policy

2.1 Information You Provide

• Account information (email address, name if provided)
• Payment information (processed through secure third-party payment processors)
• Support communications and feedback

2.2 Information Collected Automatically

• Application usage data and analytics
• Device information (operating system and version, device model, and a per-install identifier used to recognize your devices for sync and support)
• Error logs and crash reports (to improve app stability)

Microphone (mobile): The mobile app requests microphone access only to capture your speech for transcription when you start a recording. We access the microphone solely while you are dictating, and you can revoke this permission at any time in your device settings.

2.3 Audio and Transcription Data

Important: The handling of your audio recordings and transcripts depends entirely on the processing mode you choose:

• Local Whisper Mode (desktop): Audio is processed entirely on your device. We never receive, store, or have access to your audio data.
• BYOK (Bring Your Own Key) Mode (desktop): Audio is sent directly to your chosen third-party provider (e.g., Deepgram, OpenAI). We do not receive or store this data.
• Cloud Mode: Audio is processed for transcription and then discarded. We do not store audio recordings after a transcription is produced.

2.4 Mobile App and Third-Party AI Processing

When you dictate in the Contextli mobile app, your voice and the resulting text are processed by specific third-party AI providers so the app can function. We disclose them by name:

• Deepgram (speech-to-text): Your audio is sent to Deepgram, Inc. to convert your speech into text. Audio is processed transiently for transcription and is not retained by Deepgram for model training under our agreement.
• xAI / Grok (text cleanup and formatting): The transcribed text, together with the instructions of the context you selected, is sent to xAI to clean up, format, or transform the text into the output you asked for. This text is processed to generate your result and is not used to train models under our agreement.

These transfers are necessary to provide the dictation and AI-formatting features you request. Requests to these providers are made using our own API keys and are not tied to your name or account identity on the provider's side, are processed transiently to produce your result, and are not retained by the providers to train their models under our agreements. We do not send your audio or transcripts to any AI provider other than those named above, and we do not use your content to train our own models.

Cloud Sync (your choice): So your notes, contexts, and dictionary are available on all your devices, Cloud Sync is on by default and backs this content up to our secure servers. You can turn Cloud Sync off at any time in Settings, in which case your notes and transcripts are kept only on your device and are not stored on our servers. Even with Cloud Sync off, we still process basic account information (such as your email) and usage information needed to operate your account, as described elsewhere in this policy.

4.1 Local Storage

Your transcripts and notes are stored on your device, and you have full control over them: you can view, edit, or delete them at any time. If Cloud Sync is enabled (it is on by default and can be turned off in Settings), a copy is also backed up to our secure servers so your notes are available across your devices. With Cloud Sync turned off, your notes and transcripts remain on your device only.

4.2 Security Measures

We implement appropriate technical and organizational security measures to protect your information. However, no method of transmission over the Internet or electronic storage is 100% secure.