Actions VS whisper

In the latest update of the Actions app, I added an “Ask ChatGPT” action to make it easy to use ChatGPT in your shortcuts.

Hey. I'm the author of the Actions app and I'm out with a new app.

Check out the "Calculate with Soulver" action in the Actions app. It makes it easy to do calculations like that. Example

Hey, I'm the creator of the Actions app. I made this app to be able to quickly send links from my iPhone to the browser on my Mac. While making it, I realized that since you can send links to your Mac that are opened there, you could send links in the form shortcuts://run-shortcut, which would run shortcuts.

Hi. I'm the creator of the Actions app. I have made a macOS app for Stable Diffusion, which lets you create images from a text description using AI. The app includes support for running the image generation directly from the Shortcuts app. iOS support is planned.

The Actions app has a "Generate CSV" action that should be faster.

This is planned

You can use the Create Symbol Image action from my Actions app.

Let’s not talk about local models as the hardware requirements are way beyond most of these people’s reach. I have a MacBook Air with an M2 chip and 8GB of RAM and can hardly run Whisper locally, so I use this HuggingFace space.

Last week, I launched notesGPT, a free and open source voice note app that has 35,000 visitors, 7,000 users, and over 1,000 GitHub stars so far in the last week. It allows you to record a voice note, transcribes it uses Whisper, and uses Mixtral via Together to extract action items and display them in an action items view. It’s also fully open source and comes equipped with authentication, storage, vector search, action items, and is fully responsive on mobile for ease of use.

I found a pretty good discussion in the topic here:

https://github.com/openai/whisper/discussions/1243

There is a plot of language performance on their repo: https://github.com/openai/whisper

I am not aware of a multi-lingual leaderboard for speech recognition models.

I don't know how OP does it, but here's how I'd do it:

* Generate a transcript by runing Whisper against the podcast audio file: https://github.com/openai/whisper

* Upload transcript to ChatGPT and ask it to summarize.

* Automate all the above.

Ahh, that makes sense. I've been building something like that, but only from other languages into English using Whisper

Whisper already generates subtitles[0], supporting VTT and SRT so this is just a thin wrapper around that.

[0]: https://github.com/openai/whisper/blob/e58f28804528831904c3b...

> although it does require you to wear headphones so the bot doesn't hear itself and get interrupted.

Maybe you can rely on some sort of speaker identification to sort this out?

https://github.com/openai/whisper/discussions/264