Audio input should be possible from the mobile app. A local audio LLM can parse this audio and show that this is what is going to be sent to server. Or another feature could be local audio LLM just asks for yes or no from user if what it has captured is right?
Like a dictation writer.
This will allow people to set this up on a Hetzner type or local laptop server at their home and use the mobile device as input to this. Local laptop can be routed via CF tunnel.
This will be a swell AI assistant for a working person who is also doing some other activities at the same time. Like tending to kids (pushing prams or swings) or exercising or walking to grocery store.
Audio input should be possible from the mobile app. A local audio LLM can parse this audio and show that this is what is going to be sent to server. Or another feature could be local audio LLM just asks for yes or no from user if what it has captured is right?
Like a dictation writer.
This will allow people to set this up on a Hetzner type or local laptop server at their home and use the mobile device as input to this. Local laptop can be routed via CF tunnel.
This will be a swell AI assistant for a working person who is also doing some other activities at the same time. Like tending to kids (pushing prams or swings) or exercising or walking to grocery store.