feature
Conversation observability added with context_usage events in ElevenAgents
elevenlabs.ioagent
Realtime clients can now receive context_usage events after each agent turn, reporting the model name, prompt token count, and model context limit. Provides developers visibility into token usage and model resource utilization during agent interactions.
Stacks this affects
ElevenLabs ships in 5 tested stacks here.
More ElevenLabs
featurePhone keypad (DTMF) input support added to ElevenAgents conversationsreleaseElevenLabs CLI v1.0.0 released with complete API coverage and local agent managementfeatureProcedures now generally available in ElevenAgents for task-specific instructionsfeatureConversation triage ticket API added to ElevenAgents for QA and feedback