Transcribing podcasts and recordings on Mac
If you record audio, a text version helps with show notes, quotes and repurposing. WhisprDesk transcribes audio files you upload, on your Mac with a local model or through a cloud provider using your own key.
Upload a recording, get a note
Open Upload, drop in an audio file, and click Transcribe. WhisprDesk accepts MP3, WAV, M4A, WebM, OGG, FLAC, AAC, MP4, WMA and Opus files. The transcript is saved as a note, and you can copy it or export it as Markdown or plain text.
WhisprDesk works from files you already have. It does not fetch audio or video from links.
Turn a transcript into show notes
In Notes, AI actions such as Generate Notes can clean up and structure a transcript using the AI model you choose: a cloud provider with your own key, or a local model on your Mac. You can write your own actions with a name and a prompt. Review the result before you publish it.
Say titles and descriptions out loud
Dictation works in any text field where you can paste, so you can speak an episode description into your hosting dashboard or a social post instead of typing it.
Local or cloud
Where your voice goes depends on the engine you choose. With a local model (NVIDIA Parakeet is about 680 MB), transcription runs on your Mac and your audio is not uploaded. With a cloud provider, your audio goes directly to the provider whose key you entered. WhisprDesk does not receive it either way.
Unreleased episodes and guest conversations may be material you prefer to keep on your own machine. That is a good reason to choose a local model.
Frequently asked questions
- Can it transcribe a video link?
- No. WhisprDesk transcribes audio files you upload. It does not download from links.
- Does it separate hosts and guests?
- No. It produces a single transcript and does not label speakers.
- Is there a file size limit?
- With cloud transcription, files are limited to 25 MB. With a local model, WhisprDesk does not enforce a limit, but very long files have not been tested.