Philipp Hancke tests why voice agents sometimes answer their own greetings. In his setup, echo reached transcription in 21% of Edge sessions and 4% of Chrome sessions. AEC dumps show how echo cancellation, gain control, and VAD thresholds interact.
Reverse-Engineering
Google Chrome downloads a new neural AEC while you are not looking
Chrome quietly delivers a neural model that changes part of its echo-cancellation pipeline. Philipp Hancke reverse engineers the model and compares echo suppression and speech recognition against AEC3.
How OpenAI does WebRTC in the new gpt-realtime
Earlier this month, OpenAI released the GA version of its realtime API. This includes many capabilities that the Beta didnât have, including video support. I started out doing an update to the The Unofficial Guide to OpenAIâs Realtime WebRTC API I made for the Beta release last November. I discovered there were enough WebRTC updates […]
Measuring the response latency of OpenAIs WebRTC-based Realtime API
As Chad mentioned in his post last week, we have been diving into what OpenAI is doing with WebRTC. Over the last months, we actually did a full teardown and compared OpenAI’s Realtime API to what powers chatgpt.com. What intrigued us most was how to measure response latency. One of the key metrics for any […]
End-to-End Encryption in WebRTCâĶ 4 Years Later
We covered End-to-end encryption (E2EE) before, first back in 2020 when Zoom’s claims to do E2EE were demystified (not just by us; they later got fined $85m for this), followed by the quite exciting beta implementation of E2EE in Jitsi using Chromium’s Insertable Streams API. A bit later we had Matrix explain how their approach […]
