Whisper Notes - Speech to Text

Whisper Notes is a transcription tool that runs on-device, turning audio and video into text with speaker labels and no server uploads. The app supports offline transcription, multiple languages, and various input sources, including imports from other apps. It is designed for professionals who need private, on-device processing and quick transcripts.

Whisper Notes provides different speech models and languages, allowing users to choose based on language and use case. It supports exporting transcripts in SRT, VTT, or TXT formats and can auto-save transcripts to Files or iCloud Drive. The app emphasizes privacy by processing data on the device and avoiding cloud storage.

Users can edit transcripts by tapping a paragraph to fix wording, and can import audio or video from apps like WhatsApp, Photos, and Voice Memos. It offers features such as diarization (speaker labels), export options with timestamps, and the ability to summarize a transcript using external AI tools.

Whisper Notes is marketed for iOS devices, with a stated requirement of iPhone 12 and newer, and supports a wide range of languages. It offers an upfront purchase with no ongoing subscription, and includes a refund option if unsatisfied. The app is available for iPhone, iPad, and Mac, and lists the supported devices and platforms on the App Store page.

Use cases

• Transcribe meetings with speaker labels to identify who spoke
• Create subtitles from imported media for offline viewing
• Capture notes from lectures or interviews for research