The connection is bi-directional with different states.

EDIT: I fixed the issue I had with dynamic buffer allocation (I’m dynamically calculating the buffer length based on stream metrics). But will order the P4 anyway, because I want to get my hands on it.

At max I just need a few MB for reading a websocket response into internal RAM and to feed the audio loop that is running on Core 1. The issue is that the Network delivers at around 25 KB/s but the audio playback consumes 48 KB/s (buffer underrun). I can’t lower the sample rate (I tried). I’d change to another codec like Opus but Deepgram API does only support PCM (linear) at 24 KHz. I tried setting other output formats but it’s not working. Technically I could decode Opus.

The flow is this: TTS -> Websocket -> PSRAM (slow) -> I2S (DMA 8x1024) -> DAC -> Speaker

DRAM free about 50 kb, PSRAM plenty (6-7 MB)

I installed it and will test it with your settings.

I’ve implemented an ad blocking feature and a search engine result blocker by list or by domain :)

Wow! Thank you, I didn’t know this project existed. Amazing ❤️

I’ll consider this in the next few test builds. Thank you! :)

A pre-release is available for Android. If you have a free account here https://play.google.com/store/apps/details?id=com.testerscommunity you can test.

I’m currently working on the Android version.

I might have a surprise for you in version 1.0.3 (upcoming) :)

Thank you, I was looking for something like portal.mozz.us to check out a few documents :)

I’m using WhatsApp sim but Firsty is global as far as I understood

I haven’t but now I have my own :)

Firsty app, try it out

Thank you :)

This is really cool. How can I find more gemini docs?

deleted by creator

I’m glad you like it! :)

Please try updating and then try again. v1.0.2 is released.

I found the issue I believe. Fixing it.