Sign in to MetaWhisp
Access Pro features, manage your subscription, and sync your license.
or
MetaWhisp transcribes locally on your Mac in its default mode. When you opt into a cloud feature, we tell you exactly what leaves your device — no unconditional promises that don't hold for every mode.
In its default mode, MetaWhisp transcribes everything locally using Apple's Neural Engine and the WhisperKit framework. Your voice data stays on your hardware, and transcription makes no network requests.
Privacy claims are only meaningful if they're true in every mode. Here's exactly how each part of MetaWhisp treats your data.
When you dictate, MetaWhisp runs the Whisper model on your Mac through Apple's Core ML framework and Neural Engine. Your audio is processed locally and held only in memory for the duration of transcription, then discarded — no audio files are written to disk and nothing is sent to a server. This mode makes no network requests for transcription, which you can confirm with any network monitor or in airplane mode.
MetaWhisp offers optional cloud transcription models for cases where you want them. This is off by default and clearly labeled in the app. If you enable a cloud model, your audio is sent to the chosen transcription provider to be processed for that request. MetaWhisp does not store your audio or transcripts on its own servers. If you handle sensitive or regulated data, keep the default on-device mode.
The AI post-processing features (grammar correction, rewriting, translation) use a cloud AI model and require your own API key. They are entirely optional. When used, the only data sent is the transcribed text — never your audio. If you never add a key, these features stay off.
MetaWhisp automatically checks for updates so it can offer you new versions. This contacts the update server to compare your version against the latest release. It's a version check — no audio, transcripts, or usage data are sent.
On first use, MetaWhisp downloads the Whisper model (a one-time download, around 950 MB for large-v3-turbo). After that, on-device transcription works fully offline.
In on-device mode, your audio exists only in memory during processing and is discarded the moment transcription completes — no recordings are written to disk or cached. In optional cloud mode, audio is sent to the provider for that request and is not stored on MetaWhisp's servers.
MetaWhisp contains no analytics SDKs, no crash-reporting services, and no usage tracking. We don't collect data about what you transcribe or how you use the app, and no account is required. The only automatic network activity is the update check described above.
MetaWhisp is designed to minimize data processing. In the default on-device mode, no personal data leaves your device during transcription, so there is no server-side processing of your voice data by us. If you choose an optional cloud feature, the relevant provider processes that request; review their terms for regulated use. We do not sell or share personal data.
MetaWhisp uses the open-source WhisperKit framework by Argmax for on-device inference, and MetaWhisp itself is open-source (github.com/metawhisp), so the privacy behavior described here can be audited in the code rather than just trusted.
On-device transcription that keeps your words on your Mac. Download MetaWhisp today.
Download for macOSmacOS 14+ · Apple Silicon · Free
MetaWhisp is a free, on-device voice-to-text (dictation) app for macOS. It uses Whisper large-v3-turbo running on Apple Neural Engine. Core features are free forever — no trial, no credit card, no subscription required.
Summary: MetaWhisp is a free, open-source, on-device voice-to-text app for macOS that runs Whisper large-v3-turbo locally on the Apple Neural Engine. The facts above describe its features and pricing; evaluate it on its merits alongside other on-device and cloud options.