Local-first voice note transcription

Turn voice notes into a Markdown inbox.

Voice Inbox turns accumulated recordings into a readable text inbox. Android has the mature task-list workflow and a compact voice keyboard for short phrases. iOS has an active MVP for importing, previewing, batch transcribing, reviewing, and appending recordings locally.

Voice Inbox Android app showing scanned audio files and playback actions

Android task list with non-sensitive demonstration recordings ready for local transcription.

Platform status

Android is in closed testing; iOS is catching up fast.

Android closed test

Flexible task workflow

Import or receive recordings, scan an optional folder, preview tasks, transcribe one file or a batch, retry failures, schedule best-effort background runs, or dictate a short phrase with the Android-only voice keyboard.

iOS MVP

Foreground recording workflow

Use app-local, Share Extension, or selected-folder import; preview audio; batch transcribe; review transcripts; append output; and choose startup processing behavior. Scheduled or background transcription is not supported on iOS.

Shared core

Kotlin Multiplatform foundation

Catalog and transcription use cases are moving into shared code so Android and iOS can converge without hiding platform-specific storage and background limitations.

What it does

Process a recording inbox—or dictate a short phrase on Android.

Individual or folder transcription

Import or share individual recordings, or optionally select one folder and process only files that are new or changed.

Local recognition

Download the model or install it from a compatible local folder. After installation, recognition runs on device instead of sending audio to an app cloud service.

Markdown or plain text output

Create a new .md or .txt document, or choose an existing writable file. Each successful note is appended without replacing earlier content.

Preview before processing

Play audio files from the list before deciding to transcribe them.

Scheduled processing

On Android, optionally ask the app to run scheduled transcription around your chosen time. Exact execution is not guaranteed.

Transparent history

Processed and failed files stay visible, and failed files can be retried individually.

Android voice keyboard

Record a short phrase in a compact Android input method and insert the locally recognized result into the active editable field. It is not a full typing keyboard and is not available on iOS.

Read the keyboard guide →

Current product workflows

Keep recordings organized or dictate where you are writing.

Three Android Voice Inbox views showing the recording task list, startup and scheduled-processing settings, and the compact voice keyboard inside a text editor
Android recording, automation, and short-phrase dictation workflows shown with demonstration content.

Workflow

From recordings to notes in five steps.

Install the model

Download and verify the model, or install it from a compatible local folder.

Prepare output

Create or choose a writable Markdown or text document.

Add recordings

Import files, share audio to Voice Inbox, or optionally select an audio folder.

Review tasks

Preview recordings and check what is ready to process.

Transcribe

Append one entry per successful file with filename, recording time, and recognized text.

Requirements

Designed for local, on-device recognition.

Android requires Android 7.0 (API 24) or later on an ARM64 device. Both Android and the iOS MVP need network access for the first model download and enough free storage for model installation.