Why WebRTC is the wrong choice for voice AI: A technical critique of OpenAI's approach
By
atgctg
A five-star bake. Worth schmearing, sharing, saving.
Summary
A technical critique arguing against using WebRTC for voice AI applications, drawing on the author's experience rewriting WebRTC SFUs at Twitch (using Pion/Go) and Discord (in Rust). The author strongly disagrees with OpenAI's approach of using WebRTC for voice AI, advocating instead for Media over QUIC as a better alternative. The piece is a passionate, opinionated technical argument from someone with deep hands-on experience in the space.
Key quotes
· 5 pulledYou should NOT copy OpenAI.
I don't think you should use WebRTC for voice AI. WebRTC is the problem.
I ended up rewriting every protocol, because of course I did!
Just a year ago, I was at Discord and I rewrote the WebRTC SFU in Rust. Because of course I did!
Media over QUIC: There are ways to do voice AI without being traumatized by WebRTC.
You might also wanna read
VoiceAI: A Developer's Learning Path for Building Real-Time Voice Agents
A curated, developer-friendly learning path for building real-time voice AI agents, covering the full stack from speech-to-text foundations
rtcStats: Open Source WebRTC Monitoring Platform for Browser-Based Quality Metrics
rtcStats is a WebRTC monitoring and observability platform that provides real-time quality metrics from users' browsers. The open-source sol
Handoff: Transfer WebRTC Sessions from Browser to External Processes
Handoff is a GitHub project that enables developers to create WebRTC sessions in the browser and then transfer them to external processes th
Why small pull request policies can backfire on software quality
The article critiques a common software engineering policy that limits pull requests (PRs) to small sizes (e.g., 500 lines, few files). Whil
apenwarr.ca·1h agoHow Anthropic contains Claude's expanding access across its products
Anthropic describes how it has evolved its approach to granting Claude, its AI assistant, increasingly broad access to internal systems over
Testing Cursor's Jira integration: How ticket quality affects AI agent performance
Cursor launched a Jira integration that lets developers assign tickets directly to an AI agent, eliminating context switching. The author te
bit.ly·3h ago