If you have an Apple device (not just an iPhone) and an Open API Key, this shortcut is for you...
This shortcut can be used in workflows like these that has shared: There are benefits to using a "watch" folder or slack channel trigger in Make.com, but this offers another solution if you want something instantaneous that doesn't burn through executions. ❓How do we do this? Webhooks...
This is a continuation of another post that I shared last week... but much more streamlined.
📋 This shortcut will...
- Take a voice memo (or any other supported media file*)
- Transcribe the audio using whisper (Open AI)
- Pass the transcript along via webhook to another tool for further transformation
...All without having to open up separate apps or a browser.
💾 Download the shortcut to your iPhone, Mac, or iPad (or even Apple Watch... I think) here:
(File is also included below 👇)
I added a bunch of comments to the shortcut too.
*Whisper Limitations:
- Maximum content size limit: 25 MB
- Supported formats: flac, m4a, mp3, mp4, mpeg, mpga, oga, ogg, wav, webm
(So this means you could even send short mp4 videos too)
PS: You will have to accept permissions to send data to OpenAI the first time you run the shortcut on a new device. Also, your phone will display a small popup while the shortcut is running, but you can still navigate your phone while you wait for Whisper to do its thing.
PPS: You can adapt this shortcut to execute additional OpenAI requests or send other data via the webhook, but I wanted to keep it simple since this is a pretty common use case.
If you need additional context/help, let me know! Have fun!