Status

All systems operational.

Static health for the hosted service, the latency budget we hold ourselves to, and recent incident history.
Conversation LoopOperational
Median reply under a second
Speech RecognitionOperational
Streaming, committed on a silence threshold
Avatar RenderingOperational
30 to 60 fps sustained
Meeting StudioOperational
Recording and live transcripts
Avatar EditorOperational
Live 3D preview
API and WebhooksOperational
GraphQL and webhook delivery

Latency Budget

790 ms serialThe stages overlap. A partial transcript is sent speculatively, and the first clause of a response is synthesized while the rest is still generating.
  • Capture and Voice Detection40 ms
  • Speech to Text180 ms
  • First Model Token220 ms
  • First Audio Chunk190 ms
  • First Rendered Frame160 ms

Incident History

  • August 22, 2026
    Resolved
    Recording export queue backlogServer-side composition completed normally, but export delivery ran behind for a period. Live calls, transcripts and the conversation loop were unaffected.
  • May 30, 2026
    Resolved
    Avatar Editor preview failing to loadA shader compilation regression prevented the live 3D preview from initializing on a WebGL2 context with no float texture support. Resolved within the hour, and no calls were affected.