Setup guide

Get Voice Inbox ready for your recordings.

Voice Inbox works with an existing output document and user-selected audio. Android is the full folder workflow today; iOS currently supports a manual import MVP. The first model download is large, but after verification recognition runs locally.

1. Install the app

Download the latest Android APK from GitHub Releases and install it on an ARM64 Android device running Android 7.0 or later.

iOS is currently an MVP built from source rather than a store release. When Google Play or App Store listings exist, this page can link to them as the primary install paths.

2. Download the speech model

On first launch, download and verify the pinned int8 Parakeet model. The download is about 640 MiB, and installation needs about 704 MiB of free storage.

Network access is required for this first model download. Recognition runs locally after the model is installed.

3. Select an output document

Choose an existing writable .txt or .md file. Voice Inbox appends new entries and preserves existing document content. On iOS, this uses the document picker and security-scoped access.

4. Select recordings

On Android, choose one readable folder that contains audio recordings. The app scans direct children only and does not traverse nested folders.

On iOS, use the current manual import workflow to add audio files to the app-local catalog.

5. Review and transcribe

The New tab lists files that are pending or being processed. Use Play to preview a recording, then choose Transcribe All when you are ready.

Failed files move to the Processed tab with their latest error and a Retry action. Successful files are appended to the output document.

6. Optional: scheduled transcription

Open Settings to enable scheduled transcription and choose a preferred time. Android may delay background work, so scheduled runs should be treated as best-effort rather than exact alarms.

Scheduled background transcription is not part of the current iOS MVP.