Scope. This policy covers the Scribe0 iPhone app distributed on the App Store (
com.linusasaabey.scribe0ios). Scribe0 on other platforms is covered by the separate policy athttps://scribe0.com/privacy. This document is published at https://scribe0.com/privacy/ios and is the Privacy Policy URL filed for the iPhone app.
Scribe0 is provided by Linus Asaabey (“we”, “us”, “our”). This policy explains what the app does with your data. It is written to align with the Australian Privacy Principles (APP) under the Privacy Act 1988 (Cth).
Scribe0 is a dictation and documentation aid for clinicians. It transcribes speech to text on your device and can rewrite that text using an AI model. It is not a medical device and does not provide diagnosis or treatment advice.
The short version
- The app is free and has no accounts. There is no sign-in, no licence key, no subscription, and nothing to buy. Every feature is available to every user.
- Your audio never leaves your device. Speech to text runs entirely on-device on the Apple Neural Engine. We never receive, store, or transmit your recordings.
- Transcripts are stored only on your device, encrypted at rest.
- Pictures you add stay on your device. You can attach a screenshot or scan a document to give the AI context. The picture is read on your iPhone and is never uploaded; only the text read from it becomes part of your note.
- Text leaves your device only after you approve it, and only the transcript text and your prompt, never the audio. The app names the recipient and asks your permission before the first transcript is ever sent.
- The only identifier we receive is a random, anonymous device identifier sent with cloud AI requests, used solely to meter the free daily allowance. It is a random number generated at install, not a hardware identifier, and it is never used for advertising or tracking. It is not linked to your name, your email, or any account, because the app has no accounts.
- We do not run advertising or tracking. No ads, no analytics SDKs, no sale or sharing of your data for marketing.
What data the app handles
Audio recordings
Captured from your microphone solely to produce a transcript. Transcription is performed on-device; audio is held in memory only for the duration of processing and is then discarded. Audio is never written to long-term storage and is never transmitted off the device.
Photos and document scans
You can attach reference material to a dictation by picking a picture from your photo library or by scanning a page with the camera. In both cases the picture is read on your device using Apple’s built-in text recognition, and only the recognised text is kept, as part of the note’s context.
- The picture itself is never uploaded and is never sent to us or to any third party.
- Scans are not saved to your photo library and are not written to long-term storage. The image is held in memory only long enough to read the text from it.
- The app does not request access to your photo library. Picking a picture uses the system photo picker, which runs outside the app, so the app only ever receives the single item you choose. It cannot see anything else in your library.
- Camera access is requested only when you first tap Scan a document, and is used for nothing else. If you decline, every other part of the app continues to work; you can still type context or pick a picture.
The recognised text is then treated exactly like transcript text: it stays on your device, and it leaves only if you run a cloud AI prompt and approve the disclosure described below.
Transcripts and related notes
The text the app produces, plus any AI-enhanced version, is stored locally on
your device using Apple’s on-device database (SwiftData). This text can
contain personal and health information (for example, patient names,
identifiers, and clinical details). It is protected at rest by iOS file-level
encryption (NSFileProtectionComplete) and, optionally, a biometric (Face ID /
Touch ID) app lock you can enable in Settings. We do not have access to this
data.
AI enhancement
You can apply an AI “Enhance” step to a transcript. Each prompt runs in one of two places, and the app shows which:
- On-device (Apple Foundation Models, on supported hardware) processes your text entirely on the device. Nothing is transmitted.
- Scribe0 Cloud sends your transcript text and the prompt over an encrypted (HTTPS/TLS) connection to be processed by Anthropic’s Claude models running on Amazon Web Services (Bedrock) servers located in Australia, which return the enhanced text. No audio is ever sent.
Scribe0 Cloud is the only destination your text can be sent to. Text is used only to generate the result. It is not stored after the request completes and is not used to train any model. AWS model-invocation logging is disabled and our proxy does not log message content. Requests carry the anonymous device identifier described above so we can meter the free daily allowance.
Cloud processing is opt-in. Before the first transcript is ever sent, the app shows an explicit disclosure that names the AI service, states exactly what will be sent, and states what is not stored. Nothing is transmitted unless you approve it. You can decline, and on-device enhancement continues to work.
Important: transcript text sent to a cloud prompt is not redacted before sending. Do not use cloud prompts for content you would not be permitted to send to a third-party AI service under your own professional or organisational obligations.
What our servers receive
When you run a Scribe0 Cloud prompt, our proxy receives and retains only service-operation metadata: the anonymous device identifier, the model requested, timestamps, and request counts, used for daily quota metering, abuse prevention, and aggregate service statistics. We never collect, store, or log the content of your transcripts, prompts, or AI results. Quota counters expire within 48 hours.
Third parties (sub-processors)
When, and only when, you run a cloud prompt, your transcript text is processed by exactly two parties, both inside Australia:
| Service | Role | Data residency |
|---|---|---|
| Amazon Web Services (Bedrock, Australia) | Hosts and runs the Anthropic Claude models behind Scribe0 Cloud | Australian AWS regions only (Sydney / ap-southeast-2, au.* inference profiles) |
| Anthropic | Provides the Claude AI model (Claude Haiku), run on Bedrock | Australia, on Bedrock |
There are no others. The app has no bring-your-own-key option and no way to send your text anywhere else. Each service processes the text only to return the enhanced result, under its own terms and privacy policy, and each provides privacy and security protections for your data that are equal to or stronger than those described in this policy: all transfers are TLS-encrypted, AWS Bedrock does not store prompts or outputs after processing and does not use them to train models, and Anthropic’s commercial terms exclude API inputs and outputs from model training.
What we do not collect
We do not collect or transmit: your audio, any photo or scan you attach, the content of your transcripts or notes (beyond the opt-in cloud processing described above), your name or email address, payment information, hardware or advertising identifiers, location, contacts, your photo library, or browsing or search history. We do not use your data for tracking or advertising, and your text is not used to train AI models. The app contains no third-party analytics or advertising SDKs.
How long data is kept
Transcripts remain on your device until you delete them (in the app’s History) or uninstall the app. Uninstalling removes all local app data. We hold no copy of your transcripts or notes. On our servers, quota counters tied to the anonymous device identifier expire within 48 hours. Text sent to a cloud prompt is processed transiently as described above and is not retained by us.
Security
- On-device transcription, so audio never traverses the network.
- Local data encrypted at rest with iOS file protection.
- Optional Face ID / Touch ID app lock.
- All network requests use HTTPS/TLS.
Children
Scribe0 is intended for use by healthcare professionals and is not directed at children.
Your rights
Your transcripts and notes are stored locally on your device, so you control them directly: you can view, export (share), or delete them within the app at any time. Because the app has no accounts, we hold no identity records about you. If you have questions about this policy or how your data is handled, contact us at the address below.
Changes to this policy
We may update this policy as the app evolves. Material changes will be reflected by the “Last updated” date above and published at this URL.
Contact
Linus Asaabey Email: privacy@scribe0.com