Overview
This macOS desktop application (Gumroad product) performs automatic speech recognition (ASR) on audio files and returns text transcripts in over 40 languages and locale variants. The app accepts common audio formats such as mp3, wav, and caf, and is presented as a no-training-required solution using a deep neural network recognition engine. The user workflow is intentionally simple: select an audio file and press the dictate/transcribe button to produce a transcript. The product emphasizes speed, an easy-to-use interface, and privacy (claims that no personal usage data is collected). It requires an internet connection and is compatible with Mac OS (listed as Mac OS 7.0 or later on the page). The product is suited to creators, researchers, students, and professionals needing quick, low-cost multilingual transcription on macOS.
Key Features
Multilingual ASR
Transcribes audio to text across 40+ languages and regional variants (e.g., multiple English dialects).
File-based transcription
Accepts and processes common audio file formats (mp3, wav, caf) of various sizes.
No training required
Uses pre-trained deep neural models so users don't need to provide training data or model adaptation.
Simple workflow & fast search
Two-step UI (Select file -> Dictate/transcribe) and fast search over dictation content for quick retrieval.
Privacy claims
Product page states no personal or usage data collection by the vendor.


Who Can Use This Tool?
- Content Creators:Quickly transcribe interviews, podcasts, and voice notes into text for editing and subtitles.
- Researchers:Convert recorded interviews and field audio into searchable transcripts for analysis.
- Students:Transcribe lectures and study group recordings to create notes and summaries.
- Professionals:Generate transcripts from meetings and calls for documentation and compliance.
Pricing Plans
One-time purchase Mac app for multilingual audio-to-text transcription.
- ✓Supports 40+ languages (English dialects, Spanish, French, German, Portuguese, Arabic, etc.)
- ✓Transcribes mp3, wav, and caf audio files
- ✓High-accuracy speech recognition based on deep neural networks
- ✓No training required
- ✓Fast transcription and fast search of dictation content
- ✓Supports different audio file sizes
- ✓Easy-to-use interface
- ✓Requires internet connection; compatible with Mac OS 7.0 or later
Pros & Cons
✓ Pros
- ✓Low one-time price ($4.99) — affordable for casual users
- ✓Supports 40+ languages and regional dialect variants
- ✓Simple two-step workflow (select file, press dictate)
- ✓Privacy-forward claim: states no personal/usage data collected
- ✓Accepts common audio formats (mp3, wav, caf)
✗ Cons
- ✗macOS-only (desktop_macos) — not available for Windows, Linux, or mobile
- ✗Requires an internet connection (not fully offline)
- ✗Limited public presence and no independent reviews found
- ✗No free trial available
- ✗Product page lacks detailed documentation, support, or clear contact information