Transcribr Flow — Private Mac Transcription and Dictation
Drop a file, paste a media URL, or hold a shortcut to dictate into any app. Whisper runs on-device so audio never leaves your Mac. Submitted to the App Store; direct download lives at transcribr.devxgroup.io.
App Screenshots
Project Overview
Transcribr Flow is a native macOS app that turns audio into clean, timestamped text without ever touching the cloud. Whisper runs locally through WhisperKit on Apple Silicon, the cleanup pass runs through a local Ollama model, and the global hold-to-talk dictation works across any app on the system.
Three input paths cover almost every use case. Drop an MP4, MOV, MP3, WAV, M4A, FLAC, or WebM file straight onto the window. Paste a media URL and the app downloads, normalizes, and transcribes it. Or hold ⌃⌥Space anywhere on the system to record dictation that pastes into the focused app the moment you let go.
A picker covers Whisper Tiny through optimized Large v3 Turbo so the user trades speed for accuracy on their own terms. Auto language detection covers 16 languages out of the box. The optional Ollama cleanup pass strips filler words and fixes grammar, still fully offline. Output exports as plain text, SRT, or VTT, with or without word-level timestamps.
The codebase ships as two SKUs from one source. The App Store SKU runs sandboxed and supports direct media URLs only. The direct-download SKU at transcribr.devxgroup.io bundles broader URL support via yt-dlp for users who need it. Same engine, different distribution paths.
Key Features
- Fully offline — Whisper and the cleanup LLM both run on-device
- Drag-and-drop transcription for MP4, MOV, MP3, WAV, M4A, FLAC, WebM
- Live recording with real-time transcript and waveform visualization
- Media URL ingest with yt-dlp on the direct-download build
- Whisper model picker from Tiny (77 MB) through optimized Large v3 Turbo
- Auto language detection across 16 languages
- Local Ollama cleanup for grammar and filler-word removal
- Word-level timestamped export to TXT, SRT, or VTT
- Global hold-to-talk dictation (⌃⌥Space) that pastes into any app
- Sandboxed App Store SKU and notarized direct DMG from a single codebase
Tech Stack
Platforms
Project Details
2026
2 months
2 specialists
Metrics
On-device. Zero cloud dependency.
WhisperKit + Ollama on Apple Silicon
Privacy-first transcription and dictation for macOS
Business Impact
Transcribr Flow shows DevX Group's ability to ship a polished native macOS app with on-device AI on two distribution channels at once. Same codebase serves the Mac App Store under sandbox constraints and a notarized direct DMG with broader URL support. Demonstrates the engineering judgment to design around App Store guidelines without compromising the product the team actually wanted to build.
Interested in a Similar Project?
Let's discuss how we can build something great for your business.