"You have exceeded your current OpenAI Whisper API quota, please check your plan and billing details"
no idea where to check this. I have not recorded a single word so no idea where this is coming from.

Not working. I've tried paid and free accounts using "you" and "service account" API keys respectively, but every time I hit stop on the record button I get a popup saying "You have exceeded your current OpenAI Whisper API quota, please check your plan and billing details"

Apparently broken with an "Invalid OpenAI API Key" error. No guidance on how to fix, developer unresponsive.

For now it has a frustrating bug where it keeps typing "undefined" which can burn through all the 40 messages limit fast.

Edit: Pretty much as soon as the extension is enabled, it keeps writing "undefined" by itself and and sends the prompt. This happens without any intervention from me.

Edit2: The update fixed the issue. Thank you!

Fails to send microphone input to OpenAI API -- Error in console: "Content-Security-Policy: The page's settings blocked the loading of a resource at https://api.openai.com/v1/audio/transcriptions ("connect-src")." Hope this can be fixed.

Also would be nice to see the use of the OpenAI TTS for speaking the output.

Talks but does not listen. The list of playback languages is unsorted…

Clicked record , allowed everything all permissions, nothing happens, stopped the recording also does nothing

edit 2 : yes, I already tried with my chatgpt api copy pasted in the config. Is there any discord server or github somewhere so I can try to document the issue?

how cool

Die Ausgabe als Sprache funktioniert bei mir, auch wenn die Qualität sehr ernüchternd ist.

Mittels Sprache eine Eingabe zu machen habe ich aber bis jetzt nicht geschafft.

It used to work very well, but it no longer does.

Works pretty good for me, took a minute to set it up, you need to have a paid OpenAI account for it to work and you need to make an API and give the site/add-on various permissions.
After that it works great, the speech-to-text was surprisingly accurate even with my poor enunciation, the text-to-speech is an annoyingly slow speaker but maybe that's normal for TTS, I have no experience with other TTS systems. I wish it could be sped up a bit.
I also wish that when it comes to ChatGTP it would be possible to end messages early instead of having to listen to the entire thing with seemingly no way of aborting.
I did tell the AI to limit it's responses to <50 words which helped.