Welcome We want to hear your feedback! Drop a vote, leave a comment, or post a suggestion below.
Powered by
It would be great to have a better summary- Right now the AI summary is not good enough so I have to download the transcript, copy to chatgpt and ask it for a good summary with bullet points and ChatGPT does it way way better. After that I copy it to Word and save it as PDF. I guess all of this could be done automatically with NoteCat. Maybe also would be great to have an API from which I can do what I just said automatically.
Description:When using the NoteCat bot to record and transcribe conversations in Spanish, the resulting transcriptions are inaccurate. It seems that the speech recognition or AI model used is primarily trained for English, which causes it to confuse many words and mix languages.For example, common Spanish words are misspelled or replaced with English terms, making the transcripts hard to read and unreliable for meeting notes.Suggestion:It would be great if NoteCat could automatically detect the spoken language or allow users to manually select it (e.g., choosing “Spanish” before recording) to improve transcription accuracy.
Bot settings to set the default visibility for transcripts
Docs (manual) and blog for NoteCat
Hoping there will be option to turn off the AI summary.and maybe make it a manual summary that creator could add?
After using link and wanting to keep the transcription (and recording)some way to export it to file(s)
Right now you can only configure summaries to be posted in a single text channel, even if you set autorecord for all voice channels in a server. It would be great if each voice channel could configure its own channel for the summaries to be placed in. Also, it would be great if summaries could be posted directly to voice channel chats, rather than a specific text channel. This would greatly improve the functionality of the bot.It's important because some voice channels are more confidential than others, and the contents of their summaries should be limited to specific channels
When playing back audio and following along the transcript on the server, it would be great to have a feature for increasing the playback speed. I write notes from the audio and transcript but advancing through 3+ hours in real time is painful. Many thanks. Loving your service.
This is very similar to Word Replacement already available. It would be great to be able to filter out verbal crutches (uh, um, er, etc) from transcripts.I know I, for one, tend to say "ah" a lot during recording sessions, mostly to indicate thought. But the result is a lot of "uh" in the transcript that could really be cleaned out. Maybe with a default list of words, maybe with an editable list.Thank you!
Don't prompt which voice channel to record if initiated from a voice channel's text chat
When sharing the link to the recent recordings, the embed is not very clear what the link goes to. might be nice if it were a bit more detailde (which transcript it goes to, date etc)