WhisperScribe

5 export formats. Speaker recognition. Batch processing. App under 2 MB. 100% local on your Mac.

WhisperScribe transcribes audio and video files entirely on-device – no upload, no cloud. Powered by OpenAI Whisper, right on your Mac.

Export & Formats:

• Export to 5 formats: PDF, Word (DOCX), Markdown, TXT, SRT subtitles • Batch export: export all transcriptions to a folder with one click • Supported input formats: MP3, M4A, WAV, AIFF, FLAC, OGG, OPUS, MP4, MOV, MKV, AVI, WEBM • Automatic audio extraction from video files

Transcription:

• Speaker recognition: automatic [Speaker 1], [Speaker 2] labels in transcript • Rename speakers: replace labels with real names – reflected in all export formats • Batch processing: transcribe multiple files simultaneously (1–4 parallel jobs) • 13 Whisper models – from Tiny (75 MB) to Large v3 Turbo (2.9 GB) • Real-time progress with live transcript during processing • Auto language detection (100+ languages) or manual selection • Optional timestamps per segment

Smart Features:

• AI summary via local LLM (LM Studio, Ollama) – optional, no cloud service • Prompt templates for different use cases • Automatic paragraph formatting and typography

Compact & Affordable:

• App under 2 MB – models downloaded on demand • One-time purchase – no subscription needed, no hidden costs • English and German user interface

Privacy:

WhisperScribe collects no personal data, no usage statistics, and contains no trackers. Whisper models are downloaded once via HTTPS and stored locally. After download, the app works completely offline.

Perfect for:

• Transcribing interviews and podcasts – with speaker recognition • Creating meeting notes – batch process multiple recordings • Documenting lectures and talks • Generating subtitles for videos (SRT export) • Making audio content accessible

System requirements: macOS 14.0 (Sonoma) or later. Apple Silicon recommended.

Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/