# ElevenLabs pretty slow despite using inference **URL:** \ **Category:** Server SDKs\ **Tags:** agent-development\ **Created:** [May 15, 2026, 7:19am UTC](https://community.livekit.io/t/elevenlabs-pretty-slow-despite-using-inference/1132 "2026-05-15T07:19:43Z")\ **Posts on this page:** 5\ **Page:** 1
**Author:** ![Pete](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/pete/32/1355_2.png) [@Pete](https://community.livekit.io/u/Pete)\ **Post date:** [May 15, 2026, 7:19am UTC](https://community.livekit.io/t/elevenlabs-pretty-slow-despite-using-inference/1132/1 "2026-05-15T07:19:44Z")
Team, I am struggling with 11Labs performance with in Livekit. I am getting 3-4 second turnaround on Elevenlabs. I am trying to migrate from 11Labs and hence trying to keep the same setup for now, but it’s at least a second slower. Has anyone been able to get decent performance with 11Labs? Is it possible to achieve 2 seconds or less? Thanks Current stack: STT: _scribe\_v2\_realtime (temp: `0.0`, lang: `en`)_ TTS: _eleven\_flash\_v2\_5 via inference (“speed”: `0.8`, “style”: `0.5`, “auto\_mode”: `true`, “stability”: `0.8`, “sync\_alignment”: `true`, “similarity\_boost”: `0.9`, “use\_speaker\_boost”: `true`)_ LLM: _`gpt-4.1-mini, (“temperature”: `0.3)_ I am also running VAD: _“min\_speech\_duration”: `0.05`, “activation\_threshold”: `0.35`, “min\_silence\_duration”: `0.2`_ I am using preemptive generation. Library versions: ``` ```auto livekit = “^1.0.19” livekit-api = “^1.0.7” livekit-agents = “^1.3.10” livekit-plugins-openai = “^1.3.6” livekit-plugins-silero = “^1.3.6” livekit-plugins-deepgram = “^1.3.10” livekit-plugins-turn-detector = “^1.3.6” livekit-plugins-noise-cancellation = “~=0.2” ``` ``` ---
**Author:** ![darryncampbell](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/darryncampbell/32/20_2.png) [@darryncampbell](https://community.livekit.io/u/darryncampbell)\ **Post date:** [May 15, 2026, 10:00am UTC](https://community.livekit.io/t/elevenlabs-pretty-slow-despite-using-inference/1132/3 "2026-05-15T10:00:53Z")
Do you know which components are contributing to the delay? If you haven’t seen it, there is a blog to understand agent latency: > **[Understand and Improve Voice Agent Latency](https://livekit.com/blog/understand-and-improve-agent-latency)** > > Details the potential sources of latency in your voice AI solution, and which you should address as a priority It also covers using agent observability to understand which part of the pipeline the latency is coming from ---
**Author:** ![Muhammad\_Usman\_Bashir](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/muhammad_usman_bashir/32/1149_2.png) [@Muhammad\_Usman\_Bashir](https://community.livekit.io/u/Muhammad_Usman_Bashir)\ **Post date:** [May 15, 2026, 6:50pm UTC](https://community.livekit.io/t/elevenlabs-pretty-slow-despite-using-inference/1132/4 "2026-05-15T18:50:48Z")
@Pete, three levers ranked by typical savings: - STT: `scribe_v2_realtime` is slower than Deepgram streaming. You already have `livekit-plugins-deepgram`; switch to `nova-3` streaming for several hundred ms of `TTFT` savings. - TTS knobs: your params are tuned for fidelity. For latency: `style: 0`, `stability: 0.5`, `similarity_boost: 0.5`, `speed: 1.0`, `drop sync_alignment`, keep `auto_mode: true`. Each fidelity-tuned param adds server-side processing time on Flash `v2.5`. - Turn detection: swap “vad” for `MultilingualModel` from `livekit-plugins-turn-detector`. Semantic EOU often fires before your `200ms` silence window. Also, you’re on `livekit-agents==1.3.10`; latest is `1.5.9`. `inference_class="priority"` for lower-TTFT routing on LK Inference shipped in `1.5.7`. Run @darryncampbell’s observability breakdown first. The Sessions dashboard splits each turn into `STT/EOU/LLM/TTS` so you’ll know which knob actually moves your number. ---
**Author:** ![Pete](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/pete/32/1355_2.png) [@Pete](https://community.livekit.io/u/Pete)\ **Post date:** [May 28, 2026, 12:47am UTC](https://community.livekit.io/t/elevenlabs-pretty-slow-despite-using-inference/1132/5 "2026-05-28T00:47:39Z")
Thanks @darryncampbell I was able to get into more detail on the delays, thanks to your article. There were a few. I was able to improve STT by switching to Deepgram nova-3. TTS was tuned for latency performance. Both thanks to @Muhammad_Usman_Bashir I am left with LLM performance, which is abysmal. I understand geography plays a big part. Gemini 2.5 flash with 0 temp and 0 thinking budget produces 1.6 sec TTFT on average (mode) Gemini 3.1 flash lite with 0 temp and minimal reasoning effort produces 0.9 TTFT Both are faster on from Google than from Livekit inference Meanwhile, GPT 5.2 chat (0 temp, low effort) produces a larger variance of TTFT, with mode around 1.75 seconds In Elevenlabs, GPT 5.2 produces TTFT in the 400ms to 550ms _Do you guys find inference better in your experience or using directly from the vendor?_ ---
**Author:** ![darryncampbell](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/darryncampbell/32/20_2.png) [@darryncampbell](https://community.livekit.io/u/darryncampbell)\ **Post date:** [May 28, 2026, 3:43pm UTC](https://community.livekit.io/t/elevenlabs-pretty-slow-despite-using-inference/1132/6 "2026-05-28T15:43:37Z")
> [@Pete](#): > > Do you guys find inference better in your experience or using directly from the vendor? It can be, but in general you should not expect an order of magnitude improvement. > I understand geography plays a big part. The one exception is where we self-host models in LiveKit cloud colocated with the agent, example [here](https://docs.livekit.io/agents/models/stt/deepgram/#colocation), then I would expect a noticeable improvement