alt Hacker NewsMaybe 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.
Replies
fennecfoxy • today at 1:56 PM
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.
vanchor3 • today at 3:27 PM
For a model just sending occasional commands to other integrations, they're actually quite slow...
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.