LLM Streaming Question
Hey all,
I’m curious if Voiceflow will implement something in future like RETELL has, where the agent steps starts speaking as soon as it gets first tokens from LLM output, instead of waiting for the entire llm response before responding (what voiceflow is currently like)
This would be a gamechanger for voice calls because of latency reduction
I’m curious if Voiceflow will implement something in future like RETELL has, where the agent steps starts speaking as soon as it gets first tokens from LLM output, instead of waiting for the entire llm response before responding (what voiceflow is currently like)
This would be a gamechanger for voice calls because of latency reduction
