I’ve asked about this in support before. A growing number of are web calls are facing issue, where audio is being dropped at the transport layer, leading to silent failures (it says that the user hung up, but it’s clear listening to the audio that there is an issue. Last time I messaged I was told that the server pipeline was healthy.
Our team investigated thoroughly. The evidence suggests audio is dropping at the LiveKit media transport layer, which we cannot address since this is managed entirely by the Retell SDK. Our integration follows ReTell’s documentation exactly. We don’t touch the LiveKit room, ICE/TURN, remote track attachment, or media reconnection, and our backend returns 200 OK on every call creation.
These are some of the many affected call IDs:
Call_b38fbba42473db7db626594a925
Call_de3c09236b4a7e76d983e7a47ff
Call_0e16bf5caace4cb7f9b79085314
Call_244156b23956be650462ab375fa
Call_cbb69ea60d8a6fb94d83935c6ac
Call_ae8a2d40028811ebe956ab1f8bc
The transcripts point in the same direction:
- One call shows the user saying “Hello?” three times. The agent responds “I can hear you — can you hear me?” The user says “Hello?” again. ASR is transcribing speech fine, but agent audio isn’t reaching the browser. One-way audio loss at the transport layer.
- Multiple calls show users cut off mid-word and the agent prompts “still there?” repeatedly with no response. Same pattern.
- We saw one guy try 5 web calls in a single day, each with the same result. They never completed their interview.
We use the same agents, LLM, and prompts for phone and web calls. This doesn’t happen over the phone, ruling out Claude streaming gaps or LLM-side issues. It points to web call transport.
For the call IDs we provided, would you be able to share WebRTC session diagnostics? That would help us better nail down whether this is user-environment or transport-layer.
I’m spending ~$10k on ReTell a month. I need a path to resolution here. Some variation of this issue happens multiple times a day.