### Answer If your assistant sounds slow, you should check the actual latency metrics to identify where delays are occurring [(1) ]() . You can monitor latency in the Call History dashboard or retrieve it via the Get Call API . The latency breakdown includes several components : - **e2e**: End-to-end latency from when the user stops talking to when the agent starts talking - **asr**: Transcription latency - **llm**: LLM latency from the start of the LLM call to the first speakable chunk received - **tts**: Text-to-speech latency from triggering TTS to the first audio byte received Each component provides statistical fields including p50, p90, p95, p99, min, max, and individual values to help you pinpoint the bottleneck . You can also adjust agent settings that affect responsiveness [(2) ]() [(3) ]() : - **voice_speed**: Controls speed of voice, ranging from 0.5 to 2 - **responsiveness**: Controls how responsive the agent is, ranging from 0 to 1 (higher value means faster exchanges) - **enable_dynamic_responsiveness**: When set to true, the agent dynamically adjusts response speed based on the user's speech rate Check your Call History to review the latency metrics and identify which component is causing the slowness [(1) ]() .

​ To learn more, see the sources I considered: [[1] Check actual latency](https://docs.retellai.com/reliability/check-actual-latency) [[2] Get Agent Versions](https://docs.retellai.com/api-references/get-agent-versions) [[3] Get Voice Agent](https://docs.retellai.com/api-references/get-agent) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.