Show HN: ScriX – Chrome extension summarizing speech into bullet points
18 points
15 days ago
| 3 comments
| chromewebstore.google.com
| HN
zeke_the_cat
15 days ago
[-]
No explanation of how it works or how to get started. Doesn't seem to do anything.

Typical problem. Developers often fail to answer the most basic question: What is this and how do I use it?

reply
bertman
15 days ago
[-]
Looking at the code, the extension listens for `streamID` messages that are emitted whenever a user plays media in the browser[0]. It then captures the audio playback using the `MediaRecorder` interface [1] and sends the audio to the developer's backend server (wss://scrix.molyz.app/websocket) via WebSocket connection where it gets transcribed.

[0]:https://developer.chrome.com/docs/extensions/mv2/reference/t...

[1]:https://developer.mozilla.org/en-US/docs/Web/API/MediaRecord...

reply
molli
15 days ago
[-]
You watch a YouTube video or participate in a video call etc. where humans are talking. You click on the extension. You select a language. You click start. Every 30 seconds the audio gets transcribed and translated into short bullet points. The transcripts are saved. Finally, you can ask the transcript any question or transform it into a poem by Arnold Schwarzenegger - one of the great Austrian thinkers.
reply
HanClinto
15 days ago
[-]
> You watch a YouTube video or participate in a video call etc. where humans are talking.

If transcriptions of my video calls are being performed in the cloud on an untrusted server, then this feels like a big security risk...?

reply
hagbard_c
15 days ago
[-]
Yes, that's because it is a leak - just like most other cloud services by the way. Step by step, piece by piece, bit by bit the concept of 'privacy' has been hollowed out by pushing 'cloud' services (where 'cloud' stands for "someone else's computer") into just about all aspects of personal data-manipulation. This was one of the tenets of the 'Great Reset' push by the World Economic Forum which sought to capitalise (no pun intended) on the SARS2 pandemic to reshuffle the world into their vision of a new society. One of the better known publications which espoused this idea was written by Danish member of parliament Ida Auken under the title Welcome to 2030. I own nothing, have no privacy, and life has never been better. Here is is on the WEF site:

https://www.weforum.org/agenda/2016/11/shopping-i-can-t-real...

If you follow that link you'll be told they're Sorry, but we can’t find the page you were looking for. Fortunately there is the Internet Archive to save the day:

https://web.archive.org/web/20200919102818/https://www.wefor...

There is a sentence at the end of the article which refers to the death of privacy in the service of this brave, new world: Once in awhile I get annoyed about the fact that I have no real privacy. No where I can go and not be registered. I know that, somewhere, everything I do, think and dream of is recorded. I just hope that nobody will use it against me.

Since these ideas did not go down that well - which is an understatement - the lede was buried and later still removed from the site but the push towards giving up personal privacy has in no way diminished. Think of that the next time you consider using one of these 'handy' services, also the next time you log in to your cloud account. How much of your personal life did you entrust to that cloud vendor? Maybe the time has come to take it back?

reply
molli
14 days ago
[-]
These are noble values! But how to build a tool for easy transcription and summarization then?
reply
hagbard_c
14 days ago
[-]
At this moment, not just yet. Once either the models have come down in size or hardware has caught up with the demands so they can be run locally it will become feasible to offer such functionality in a way which does not sacrifice privacy to convenience.
reply
molli
15 days ago
[-]
I know what you mean. But I can't run the transcription and llm locally on the user's machine. So it has to be in the cloud. And most video calls and transcription/translation services are in the cloud anyway. So yes, you have to trust that the backend is secure, and it is.
reply
coldtrait
14 days ago
[-]
What about an Austrian born painter?
reply
drcongo
15 days ago
[-]
From the name I was expecting it to turn speech into dubstep.
reply
molli
15 days ago
[-]
Coming soon
reply
coldtrait
14 days ago
[-]
Tried it on a youtube video and it doesn't work.
reply
molli
14 days ago
[-]
Did you click start and nothing happened? The service is up and running..
reply
coldtrait
14 days ago
[-]
I clicked on the extension icon and it didn't work. I don't see anything for it on any youtube video page either.
reply
molli
14 days ago
[-]
Can't reproduce it right now, but I'll look into it. Normally, it would show a button to sign in with google.
reply
coldtrait
8 days ago
[-]
I was using it on Edge, which usually supports chrome extensions directly. So maybe that's why.

Tried it on chrome. Could sign in, but doesn't work after that nor does it maintain my login session. Each time I click on the extension it prompts me to sign in with google.

reply