How OpenAI delivers low-latency voice AI at scale
1–10 of 172 posts
Re: How OpenAI delivers low-latency voice AI at scale
#2so is the answer
WebRTC + Kubernetes
Re: How OpenAI delivers low-latency voice AI at scale
#3I hate the voice ai though, it's so much dumber
Re: How OpenAI delivers low-latency voice AI at scale
#4It's missing the part where they explain how they obtained the training data for their voice AI.
Re: How OpenAI delivers low-latency voice AI at scale
#5> Voice AI only feels natural if conversation moves at the speed of speech […] At OpenAI’s scale, that translates into three concrete requirements: Global reach for more than 900 million weekly active users
Surely the number refers to the total users of ChatGPT overall, and the fraction of those who use voice features is considerably smaller, is it not?
That’s the kind of thing that influences business decisions like knowing how much hardware and software optimization to throw at a problem.
Re: How OpenAI delivers low-latency voice AI at scale
#6if anyone is looking to get into this. pipecat is a great open-source repo and community. https://github.com/pipecat-ai/pipecat
Re: How OpenAI delivers low-latency voice AI at scale
#7if anyone is looking to get into this. pipecat is a great open-source repo and community. https://github.com/pipecat-ai/pipecat
I've been looking at this! Great project.
Re: How OpenAI delivers low-latency voice AI at scale
#8I hate the voice ai though, it's so much dumber
Fwiw - I found the advanced AI voice feature to be actually detrimental. It's good if you just want a single sentence answer. I've turned it off though when I want a more detailed, structured, considered answer.
Re: How OpenAI delivers low-latency voice AI at scale
#9[flagged]
Re: How OpenAI delivers low-latency voice AI at scale
#10if anyone is looking to get into this. pipecat is a great open-source repo and community. https://github.com/pipecat-ai/pipecat
I wish I had known about Pipecat a lot sooner. I found out about it a few weeks back, and since Gemma 4 launched, I've been building my own entirely local voice assistant using Gemma 4 + Kokoro TTS + Whisper from scratch - https://github.com/pncnmnp/strawberry.
Pipecat's smart turn model is really good for VAD - https://huggingface.co/pipecat-ai/smart-turn-v3