Spokenly uses a layered privacy protection scheme:
- local processing mode: When using the Whisper model all voice data is saved on the user's device (path ~/Library/Spokenly/Transcriptions) and is not uploaded to the cloud.
- Cloud Model Specification: Audio is instantly deleted and not stored even when using a cloud model such as GPT-4o, users can view third party privacy policies
- privilege control: The application explicitly requires microphone and accessory function permissions, which can be managed by the user at any time in the system settings
Network Requirements Aspects:
- Native Whisper models are fully supported for offline use without the need for an internet connection
- Cloud Advanced Modeling requires a stable internet connection and is recommended to be used in a Wi-Fi environment for the best experience.
- Video file transcription has no special network requirements and relies heavily on local computing performance.
This answer comes from the articleSpokenly: a speech-to-text tool for macOSThe
May not be reproduced without permission:AI productivity tools " How does Spokenly protect user privacy? What are the network environment requirements?
English 
简体中文 
日本語 
Deutsch 
Português do Brasil