Comment by numpad0
6 hours ago
Maybe it's LLM and human actor splitting work, but she looks too natural, too fast and too error-free to be LLM based since too long ago. Just their dictation -> thinking -> TTS loop is too fast to be LLM. Context awareness and character adherence is too perfect as well.
Because Vedal is apparently obsessed with latency, and running the model locally.
Even if it were a human, that would require both fast typing and a fast TTS.
For a model just sending occasional commands to other integrations, they're actually quite slow...
Never seen Taalas?
Let alone a decent sized model on a couple 4090s or similar, pretty gud t/s to churn out tts/stt/response/control model actions and emotes.