Private and open-source alternatives to Apple Dictation
12 dictation and transcription rated against the same public privacy criteria as Apple Dictation (macOS Dictation, iPhone Dictation), with our picks first.
Why look for an alternative?
- Open source: no. Closed source.
- No trackers or telemetry: partial. No third-party trackers, but Apple collects request data such as device configuration and performance statistics by default, under a rotating random identifier.
- Independent audit: no. No independent audit is published.
- Runs on the device: partial. Supported languages and devices process dictation on the device; otherwise audio is sent to Apple servers.
See the full Apple Dictation rating.
The alternatives
Buzz Grade B
Desktop app that transcribes and translates audio and video files or live microphone input offline using Whisper models. It can optionally use the OpenAI Whisper API instead.
Buzz scores 87 out of 100 (grade B) on the dictation and transcription criteria. It meets 5 of 6 criteria: open source, no trackers or telemetry, no ads or data sales, runs on the device and no training on recordings.
Handy Grade B
Free, open-source desktop app for push-to-talk dictation. Speech is transcribed offline on the device with local Whisper or Parakeet models and typed into the active text field.
Handy scores 87 out of 100 (grade B) on the dictation and transcription criteria. It meets 5 of 6 criteria: open source, no trackers or telemetry, no ads or data sales, runs on the device and no training on recordings.
Whisper Grade B
Open-source speech recognition model and Python command-line tool from OpenAI that transcribes and translates audio in many languages on the local computer.
Based in the United States (Five Eyes). Whisper scores 87 out of 100 (grade B) on the dictation and transcription criteria. It meets 5 of 6 criteria: open source, no trackers or telemetry, no ads or data sales, runs on the device and no training on recordings.
whisper.cpp Grade B
C/C++ port of OpenAI's Whisper speech recognition model that runs transcription on the CPU or GPU of the local device. Used as a library and command-line tool, and as the engine inside many dictation apps.
whisper.cpp scores 87 out of 100 (grade B) on the dictation and transcription criteria. It meets 5 of 6 criteria: open source, no trackers or telemetry, no ads or data sales, runs on the device and no training on recordings.
Anarlog Grade D
Open-source, local-first meeting notepad, formerly Hyprnote, that records device audio without a bot and creates transcripts and AI summaries. Transcription can run on the device on supported Macs or through a chosen cloud provider.
Based in the United States (Five Eyes). Anarlog scores 57 out of 100 (grade D) on the dictation and transcription criteria. It meets 3 of 6 criteria: open source, no ads or data sales and no training on recordings.
MacWhisper Grade D
macOS app that transcribes audio and video files, meeting audio and dictation with local Whisper-based models, including speaker labels and subtitle export.
MacWhisper scores 57 out of 100 (grade D) on the dictation and transcription criteria. It meets 3 of 6 criteria: no ads or data sales, runs on the device and no training on recordings.
Meetily Grade D
Desktop meeting assistant that records meeting audio without a bot, transcribes it on the device with Whisper or Parakeet models, and generates summaries with local or user-chosen AI models.
Meetily scores 57 out of 100 (grade D) on the dictation and transcription criteria. It meets 3 of 6 criteria: no ads or data sales, runs on the device and no training on recordings.
VoiceInk Grade D
Dictation app for macOS and iOS that transcribes speech with local Whisper, Parakeet or Apple models and inserts the text into any app. Cloud transcription and AI text enhancement are optional.
VoiceInk scores 57 out of 100 (grade D) on the dictation and transcription criteria. It meets 3 of 6 criteria: no ads or data sales, runs on the device and no training on recordings.
Superwhisper Grade D
Dictation app that turns speech into text in any app, with optional AI formatting. It offers local Whisper, Parakeet and Cohere models as well as cloud voice and language models.
Superwhisper scores 43 out of 100 (grade D) on the dictation and transcription criteria. It meets 2 of 6 criteria: no ads or data sales and no training on recordings.
tl;dv Grade F
Cloud meeting recorder that joins Google Meet, Zoom and Microsoft Teams calls as a bot, then records, transcribes and summarizes them and can sync notes to CRMs.
Based in Germany (Fourteen Eyes). tl;dv scores 29 out of 100 (grade F) on the dictation and transcription criteria. It meets 3 of 10 criteria: no ads or data sales, TLS configuration and no training on recordings.
Granola Grade F
AI notepad for meetings that captures computer audio without a bot joining the call, transcribes it through cloud providers, and turns the user's notes and the transcript into meeting summaries.
Based in the United States (Five Eyes). Granola scores 26 out of 100 (grade F) on the dictation and transcription criteria. It meets 1 of 10 criteria: TLS configuration.
Aqua Voice Grade F
Voice dictation app that sends speech to the cloud for transcription with its own Avalon model and inserts formatted text into any app, with optional screen context for accuracy.
Based in the United States (Five Eyes). Aqua Voice scores 24 out of 100 (grade F) on the dictation and transcription criteria. It meets 1 of 10 criteria: TLS configuration.