We have not seen any further errors after the fix was applied. All services are fully operational and stable. We will post an RCA on our status page after further investigation.

Our engineers have applied a fix for the likely root cause. We are seeing signs of recovery but we will continue to monitor until recovery is fully confirmed.

We have isolated the cause of the increased latency and errors, and are working to resolve it. Current evidence suggests that the Sound Effects product and other Creative Platform products may also be affected, but scope and severity of impact to these products remains unclear.

We are currently investigating increased latency, conversation failures, and API request failures currently known to affect Agents and STT. These failures may manifest as delays in agent conversations, 429s to STT requests, or conversation failures with the error: "START node generated a response after progressing".