Frequently Asked Questions

Is my audio really private?

Yes, 100%. LocalWhisper runs entirely on your Mac using the Whisper AI model. Your audio never leaves your device, not even for a millisecond. We have zero servers, zero accounts, and zero way to access your data.

What’s the difference between model sizes?

Smaller models (tiny, base) are faster but less accurate. Larger models (small, medium, large) are more accurate but use more memory and take longer. We recommend starting with ‘base’ for the best balance. Apple Silicon Macs can easily run the ’large’ model.

Does it work offline?

Absolutely. After the initial model download (from HuggingFace), LocalWhisper works completely offline. No internet connection required for transcription.

What languages are supported?

Whisper supports 99 languages and can auto-detect the language being spoken. The full list includes: Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Bashkir, Basque, Belarusian, Bengali, Bosnian, Breton, Bulgarian, Cantonese, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Faroese, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Lao, Latin, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Myanmar, Nepali, Norwegian, Nynorsk, Occitan, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Sanskrit, Serbian, Shona, Sindhi, Sinhala, Slovak, Slovenian, Somali, Spanish, Sundanese, Swahili, Swedish, Tagalog, Tajik, Tamil, Tatar, Telugu, Thai, Tibetan, Turkish, Turkmen, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, Yiddish, and Yoruba.

Will it work on my Mac?

LocalWhisper requires macOS 11.0 (Big Sur) or later. It works on both Apple Silicon (M1/M2/M3/M4) and Intel Macs. Apple Silicon Macs get hardware acceleration via Metal for faster transcription.

How is this different from Apple Dictation?

Apple Dictation sends audio to Apple’s servers for processing. LocalWhisper processes everything locally using OpenAI’s Whisper model, which often provides better accuracy, especially for technical terms, names, and non-English languages.

How does LocalWhisper compare to SuperWhisper?

Both apps use OpenAI’s Whisper model for local transcription. LocalWhisper includes file transcription with every license, a feature SuperWhisper charges extra for as a ‘Pro’ upgrade. We also offer a simpler one-time purchase with no subscription, encrypted local history, and support for transcribing long-form audio like podcasts and audiobooks.

What’s included in the free version?

The Free tier includes unlimited dictation with no word or time limits, all model sizes (Tiny to Large), 99 languages with auto-detect, and 100% offline processing. No account or credit card required. When you’re ready for features like audio file transcription and LLM refinement, upgrade to Standard.

Is there a subscription?

No. LocalWhisper’s Free tier is free forever. Paid tiers (Standard at $29, Pro at $99) are one-time purchases. You pay once and own it forever. All updates are free.

What about Windows/Linux support?

Windows and Linux support are planned for Q1 2026. We’re currently focused on perfecting the macOS experience first.

Can I use it for sensitive/medical/legal transcription?

Yes. Because all processing happens locally on your device, LocalWhisper is suitable for HIPAA, GDPR, and other compliance requirements. No PHI or sensitive data ever leaves your Mac.

How do I get support?

Visit our Contact & Support page to get in touch. We’re happy to help!