I don't think that's the primary purpose of realistic interactive avatars, any more than deception is the purpose of CGI. Deception requires intent to mislead — if users know they're talking to an avatar, it's not deception no matter how realistic. Just as moviegoers aren't "deceived" by CGI. It's an experience they opt into.
As for benefits: language learning with avatars, scalable corporate training, accessible education for kids, personalized coaching, and certainly entertainment, which has real value too.
Do you think the same about text that is indistinguishable from human-written text (LLM chatbots)? Or voice that is indistinguishable from a human talking?
Illegal things, like fraud and impersonation, are illegal. There's a difference between the tool and the actions people do with the tool.
There are tons of useful applications of interactive avatars - from corporate training to kids education to language learning and more. Plus, why would you want to stop this little guy from existing in the world? :) https://lemonslice.com/try/alien
This is so obvious now that you say it (* facepalm *). We definitely need to give the LLM context on the appearance (both from the initial image as well as any /imagine updates during the call). Thanks for pointing it out!
This is good feedback thanks! The "not patient" feeling probably comes from our VAD being set to "eager mode" so that the latency is better. VAD (i.e. deciding when the human has actually stopped talking) is a tough problem in all of voice AI. It basically adds latency to whatever your pipeline's base latency is. Speech2Speech models are better at this.
Good idea. We need to do that. I'm also excited to push the /imagine stuff further and have B-roll interspersed with the talking (like a documentary) or even follow the character around as they move (like a video game)
I wonder if we should make the UI a more common interface (e.g. "the call is ringing") to avoid this confusion?
It's a normal mp4 video that's looping initially (the "welcome message") and then as soon as you send the bot a message, we connect you to a GPU and the call becomes interactive. Connecting to the GPU takes about 10s.
This is a good point on audio. Our main priority so far has been reducing latency. In service of that, we were deep in the process of integrating Hume's two-way S2S voice model instead of ElevenLabs. But then we realized that ElevenLabs had made their STT-LLM-TTS pipeline way faster in the past month and left it at that. See our measurements here (they're super interesting): https://docs.google.com/presentation/d/18kq2JKAsSahJ6yn5IJ9g...
But, to your point, there are many benefits of two-way S2S voice beyond just speed.
Using our LiveKit integration you can use LemonSlice with any voice provider you like. The current S2S providers LiveKit offers include OpenAI, Gemini, and Grok and I'm sure they'll add Personaplex soon.
As for benefits: language learning with avatars, scalable corporate training, accessible education for kids, personalized coaching, and certainly entertainment, which has real value too.