Reads selected text using the Gemini 2.5 TTS model, then automatically downloads the audio file.
Reads selected text using the Gemini 2.5 TTS model, then automatically downloads the audio file.
You'll need to get a Google AI Studio API key first. A free one will do.
After entering your API key, set the hot-key and voice prompt. (The defult hotkey may not work.)
The main use for me is making anki cards to learn English when I browse random articles online. Please don't use this to generate AI slop to post online.
Update: The rate limit for one key(project) per day is 10 requests. You'll probably need to apply for multiple projects (and get one API key for each project.
I made an Anki version of this so you can generate the audio file in anki without the dragging process.
https://ankiweb.net/shared/info/89648149?cb=1768926186756
