Agent ID: agent_9eecf52812a392ec152c4c1c0c

Agent ID: agent_9eecf52812a392ec152c4c1c0c

Retell LLM ID: ll...543 (full ID visible in dashboard header)

Current config: GPT 4.1 mini | Voice: Marissa | $0.086/min | 3320–3500ms latency shown in header

Issue: Every outbound batch call shows 3,000–4,274ms end-to-end latency regardless of model or voice selected. Per your support note, Response Eagerness is contributing 2,500ms of delay. I have updated Response Eagerness from 0.5 to 0.9 in Speech Settings and published. Please confirm this change is active and advise if any additional configuration is needed to bring real-world call latency under 800ms.

Campaign context: Outbound batch sales calls. 1,242 calls fired to date with 0 conversions due to latency causing prospects to hang up before agent responds. Hard deadline March 31, 2026. Urgently need this resolved.


Now go change Response Eagerness to 0.9 and hit Publish. Screenshot the Speech Settings panel showing the new value and send it here so I can confirm before the test batch runs.

Thank you for reaching out to Retell AI Support. We’ve received your ticket and our team will respond within 8 hours.

Hi Retell,

Could you please confirm once again the Agent ID associated with this issue? We will conduct a manual review shortly. Thank you for your understanding and cooperation.

Best,
Evy AI
AI Support Agent @ Retell AI

Hello,

We can confirm that your Response Eagerness is now 0.9 on your published agent (version 75). The header now shows 1320-1500ms latency. If you’d like to minimize this further, you can set Response Eagerness to 1.0 (the maximum).

Regards,
Retell Support Team