Keeping Transcriptions Private

By default, transcriptions (including Speaker Identification) is all performed locally on your Mac or iOS device, and transcription data doesn't leave the local device.

It does this by first downloading a transcription model (such as Whisper or Parakeet) to your computer and running it with your files locally.

However, the following additional features do involve transmitting data to the cloud:

• If you use a Cloud Transcription provider (such as Groq, ElevenLabs or Deepgram), then instead of performing the transcription on your machine it instead sends the audio to a server owned by that cloud provider, and the transcription result is sent back to MacWhisper.
• If you use DeepL Translation (in order to translate your transcription to another language), the transcription is sent to DeepL's servers for processing in order to produce a translation.
• If you use an AI Prompt then your transcription is sent for processing by an AI Service Provider (such as OpenAI, Anthropic, etc).
  • The exception to this is if you use a local AI Service Provider such as Ollama or LM Studio, which runs locally on your Mac. That way, MacWhisper can get AI Prompt responses without using the internet.