A loosely moderated place to ask open-ended questions
Search asklemmy 🔍
If your post meets the following criteria, it’s welcome here!
- Open-ended question
- Not offensive: at this point, we do not have the bandwidth to moderate overtly political discussions. Assume best intent and be excellent to each other.
- Not regarding using or support for Lemmy: context, see the list of support communities and tools for finding communities below
- Not ad nauseam inducing: please make sure it is a question that would be new to most members
- An actual topic of discussion
Looking for support?
Looking for a community?
Icon by @Double_A@discuss.tchncs.de
- 0 users online
- 233 users / day
- 946 users / week
- 2.44K users / month
- 5.59K users / 6 months
- 1 subscriber
- 3.07K Posts
- 119K Comments
- Modlog
Whisper is open source and free AI model for transcription. If you’re not comfortable setting it up Audacity has a whisper plugin you can easily add and use.
As to how good it is, it really varies a lot but it is free. You need another plugin to export to a subtitle file.
Edit: Actually the program Subtitleedit (https://www.nikse.dk/) has the ability to run whisper models and you can download them from within the app, also no need for another plug to export so that’s probably the easiest. Once it’s as text you can use the translate menu within SE to translate. You need an API key (paid) for most of the truly good services but you can use basic google translate for free and it should give you the gist of things.