# High Latency (~2–3s) in LiveKit Voice Agent with Plivo

**URL:** <https://community.livekit.io/t/high-latency-2-3s-in-livekit-voice-agent-with-plivo/675>\
**Category:** Getting Started\
**Created:** [March 25, 2026, 3:02pm UTC](https://community.livekit.io/t/high-latency-2-3s-in-livekit-voice-agent-with-plivo/675 "2026-03-25T15:02:18Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Anil\_Mohite](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/anil_mohite/32/270_2.png) [@Anil\_Mohite](https://community.livekit.io/u/Anil_Mohite)\
**Post date:** [March 25, 2026, 3:02pm UTC](https://community.livekit.io/t/high-latency-2-3s-in-livekit-voice-agent-with-plivo/675/1 "2026-03-25T15:02:18Z")

</div>

Hi team,

I’m using LiveKit 1.5 with Plivo for outbound voice calls and facing latency around ~2–3 seconds before the agent starts speaking.

I’ve already optimized prompt size and reduced tokens significantly, but still seeing noticeable delay in first response.

Is this expected with LiveKit + Plivo, or are there recommended optimizations (pipeline config, streaming, prefetch, etc.) to reduce initial response latency further?

Would appreciate any guidance or best practices 🙏

---

<div class="post-metadata">

**Author:** ![CWilson](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/cwilson/32/135_2.png) [@CWilson](https://community.livekit.io/u/CWilson)\
**Post date:** [March 25, 2026, 3:29pm UTC](https://community.livekit.io/t/high-latency-2-3s-in-livekit-voice-agent-with-plivo/675/2 "2026-03-25T15:29:46Z")

</div>

A 2–3s first-response delay is not inherently expected, but it’s common in STT → LLM → TTS pipelines over telephony due to accumulated latency (STT finalization + turn detection + LLM + first TTS chunk + SIP media path).

To reduce perceived latency:

- Enable **preemptive generation** so LLM/TTS start before end-of-turn detection completes: see the Performance optimization section of [Agent sessions](https://docs.livekit.io/agents/logic/sessions/) and [Preemptive speech generation](https://docs.livekit.io/agents/multimodality/audio/#preemptive-speech-generation).

- If this is on initial connect, use **instant connect (pre-connect audio)** to buffer speech while connecting: [Instant connect](https://docs.livekit.io/agents/multimodality/audio/#instant-connect).

- Use Agent observability to measure where time is spent (STT vs LLM vs TTS).

Are you using the STT–LLM–TTS pipeline or a realtime speech-to-speech model, and which STT/TTS providers are configured?