Whisper STT
Local speech-to-text in 90+ languages. Transcribe meetings, interviews, voice notes — all on your Mac.
What is Whisper STT?
Whisper is OpenAI's state-of-the-art speech recognition model, and MacAI installs it to run entirely on your Mac. It can transcribe audio in over 90 languages with remarkable accuracy, handling accents, background noise, and technical jargon that other transcription services struggle with.
Unlike cloud transcription services like Otter.ai or Rev that charge per minute and upload your audio to external servers, Whisper runs 100% locally on your Apple Silicon. Your meetings, interviews, legal depositions, and medical dictations never leave your machine — making it the gold standard for privacy-sensitive transcription.
The model supports multiple output formats including plain text, SRT subtitles for video, and timestamped JSON for programmatic processing. It can also translate speech from any supported language directly into English, making it a powerful tool for multilingual teams and content creators.
MacAI configures Whisper with the optimal model size for your hardware — from the lightning-fast "tiny" model for real-time dictation to the highly accurate "large-v3" model for professional-grade transcription. We also set up convenient command-line shortcuts and integration with other MacAI services.
How It Works
From audio to text — fast, accurate, and completely private.
What You Get
- Whisper model installed — optimised model size selected for your Mac's RAM and processor
- Multi-format export — plain text, SRT subtitles, VTT, and timestamped JSON output
- 90+ language support — including Cantonese, Mandarin, English, Japanese, Korean, and more
- Translation mode — automatically translate any language to English during transcription
- Batch processing scripts — transcribe entire folders of audio files in one command
- Real-time dictation — live microphone transcription for note-taking
- Quick-start guide — cheat sheet with common commands and best practices
Who Is This For?
Journalists
Transcribe interviews and press conferences quickly with timestamps for easy reference.
Legal Professionals
Confidential deposition and meeting transcription that never touches the cloud.
Content Creators
Generate subtitles for videos in SRT format — no monthly subscription needed.
Medical Professionals
Dictate clinical notes privately with HIPAA-friendly local processing.
Get Whisper STT on your Mac
Professional transcription. Zero cloud dependency. One-time setup.