Interesting approach using Signal for the transport layer. I&#x27;ve been working with real-time audio pipelines (chrome.tabCapture → Whisper) and the latency tradeoff between STT chunk size and accuracy is always tricky. What&#x27;s the end-to-end latency like on a video call?

Hi! thanks for the feedback!I think you are right. I thought &quot;Call&quot; would clearly get the idea of voice across at least, but it can be confused with function call, or simply to invoke.I dont have the ability to change the title but if someone else wants to:&quot;Video and Voice Call an AI from Signal&quot;Else maybe I will submit it again in a few days.Thanks

Title being updated from its current form to add that this is specifically voice and video would make it quite a bit more interesting. Using text to invoke an AI from Signal is not really interesting at all, that’s basically OpenClaw. Using voice and video to do so, however, is quite a bit more interesting

Hecate is an AI you can voice and video call from Signal iOS and Android. This works by installing Signal into an Android emulator and controlling the virtual camera and microphone. Tinfoil.sh is used for private inference.

Show HN: Hecate – Call an AI from Signal

Comments

swq115

SOLAR_FIELDS

rhodey