Open Source Voice AI: How We Built ChatGPT's Voice Mode Infrastructure
watch on portal.gitnation.org ↗https://portal.gitnation.org/contents/open-source-voice-ai-how-we-built-chatgpts-voice-mode-infrastructuresummary
Describes how OpenAI used LiveKit's open source stack to build the production infrastructure for ChatGPT’s Advanced Voice Mode, focusing on architecture choices for scale, reliability, and low latency. Covers technical and business reasons for choosing open source, concrete scaling challenges and metrics from millions of calls, lessons learned and trade-offs, plus how others can reuse the same stack for their voice AI projects.
AI-written summary · about
related talks
23mBuilding with OpenAI: What's Ahead
21mBuilding a Voice-Enabled AI Assistant With Javascript
01h 26mBuilding voice agents with OpenAI
51mBuilding an AI assistant that makes phone calls
26mEnabling the next generation in voice technology
39mLive voices with LiveView
44mSmartly AI: Cross Platform Voice Application Creation
28mScrew the Browser! Build ChatGPT via SMS