Multimodality and streaming is hard. I've been building something that allows you connect streaming…
Jaana Dogan ヤナ ドガン
Visit on X@rakyll167K followers
17,851 views
Multimodality and streaming is hard. I've been building something that allows you connect streaming devices like screen capture, microphone, camera, and text easily to craft generative streaming pipelines.
It works well with Gemini 2.0 models. Happy to open source if anyone wants it.
10 Comments
Comments from the original post on X (Twitter)

@rakyll
It allows building pipelines with a little bit of configuration. It's super easy to quickly see what the models are capable of given a mixture of different modalities and context including custom components that can augment the context.
18 likes

@notdjkhaled7
I’d like to use that
3 likes

@Xinanexa
please do!
2 likes

@samuel_n7
Really interested in something like this
1 like

@FakeMcFakeyFace
👀

@kau_mad
eggcellent! I'd like to try it.

@jcollery
Yes please!🙏

@_5upr4
Very cool! I built a similar thing in python a couple months ago before all the realtime stuff came around. It's already open-source here:

@00x1337
+1 👆

@Kesav_Sundar
Yes, please.
