#๐ I have the basic microphone input code set up, now I'm not sure where to go from here.
19 messages ยท Page 1 of 1 (latest)
@lone sinew
Remember to:
- Ask your Python question, not if you can ask or if there's an expert who can help.
- Show a code sample as text (rather than a screenshot) and the error message, if you've got one.
- Explain what you expect to happen and what actually happens.
:warning: Do not pip install anything that isn't related to your question, especially if asked to over DMs.
The overall project in mind is a simple AI assistant, so eventually itll need command parses or w/e. But I'm taking it one step at a time. As far as I know what I have is at least the first step relatively done for input. But I imagine next I have to code something to determine whats actual speech vs noise
I plan to use faster-whisper for the STT
well, if your are making an assistant like Alexa(with ai if you want) this is a great tutorial
It uses LiveKit which covers most of the boring/hard things and all you have to do is write code for tools.
If you want to instead make it from scratch, that is fine too and I can help you.
This is a good one it only shows the setup and you have to code the tools yourself. If you want to make it from scratch that is fine too.
Btw he has a repo with the code which you can clone
and you don't have to follow the tutorial and it will be a good base
If you wanna do it from scratch that's fine too
I can help with that
I planned to do it from scratch
so since you already have the audio input
Maybe feed it into the gemini API?
gemini has a free API teir with 1000 calls per month or day I think
This help channel has been closed. Feel free to create a new post in #1035199133436354600. To maximize your chances of getting a response, check out this guide on asking good questions.