Wisply features
Record a conversation. Make sense of it later.
Transcription, speaker labels, and tools for reviewing your notes on Mac, iPhone, and iPad. Available features depend on your device and plan.
Record and transcribe
Live transcription
Follow speech as text while you record. Transcription uses on-device speech recognition; supported languages and model downloads depend on your device.
Speaker labels
Distinguish speakers with names and colors in the transcript. Speaker profiles can help identify returning voices. Review labels when voices overlap or the recording is noisy.
Microphone and system audio on Mac
Record your voice and audio from supported apps together. System audio capture needs the relevant macOS permissions, and app restrictions may affect what can be recorded.
Apple Watch voice memos
Record a memo on your Apple Watch and send it to your paired iPhone for transcription and review.
Review a conversation
Summaries and action items
Supported local AI models can summarize a recording and suggest action items or quotes. These features need compatible hardware, Apple Intelligence, and available models. Check the result against your transcript.
Questions about your notes
Use supported AI features to ask questions or find details in a transcript. Local and cloud options have different device and provider requirements.
Playback and search
Keep recordings, transcripts, and insights together. Search your library or use the recording timeline to return to a particular moment.
Recording controls on Mac
Use menu bar controls, keyboard shortcuts, and floating widgets to manage recording and follow the transcript while you work.
Keep using your notes
Export and sharing
Export a transcript for use outside Wisply. Optional Obsidian export saves recordings as Markdown notes with transcript text and available insights in your vault.
Optional iCloud sync
Enable sync to share transcript and memo data across your devices through your iCloud account. Saved audio recordings stay local.
Screen Understanding on Mac
This optional feature recognizes text from one window or display you choose. It is off by default, requires confirmation for each session, and stays visibly indicated while capture is active. Frames and text are processed locally.
In Interview Setup, you can review recognized text in a question and choose to send that question to a cloud model after consent. This workflow sends the question text, without uploading screen images or video frames.
Local processing and optional services
Core transcription, speaker identification, and supported local AI insights run on your device. Saved audio stays local, and transcripts and memos are stored locally by default.
With your consent, optional cloud AI can send audio, text, or context to your chosen provider, including live microphone audio for supported features. If you connect your own provider account, its usage charges are separate. Usage and diagnostic analytics are enabled by default.
Read the privacy policy