---
type: "post"
id: "augment-your-livekit-agent-with-modal-gpus-3c5d04"
slug: "augment-your-livekit-agent-with-modal-gpus-3c5d04"
title: "Augment Your LiveKit Agent with Modal GPUs"
description: "Modal published a tutorial showing how to pair LiveKit Agents with custom models hosted on Modal GPUs."
retrieval_nugget: "Modal published a tutorial showing how to pair LiveKit Agents with custom models hosted on Modal GPUs."
published_at: "2026-10-24"
updated_at: "2026-10-24"
record_date: "2026-10-24"
date_kind: "published_at"
topics: ["generative-media","multimodal"]
entities: ["Modal","LiveKit","LiveKit Agents","BitHuman","Expression Video Avatar","Qwen3-TTS"]
related_patterns: ["generative-media-becomes-application-infrastructure"]
novelty_label: "new_fact"
what_changed: "Modal published a tutorial on augmenting LiveKit agents with Modal GPUs, including open-weight and custom models."
prior_refs: []
source_url: "https://modal.com/blog/livekit-modal"
source_urls: ["https://modal.com/blog/livekit-modal"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:augment-your-livekit-agent-with-modal-gpus-3c5d04"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/augment-your-livekit-agent-with-modal-gpus-3c5d04/","markdown":"https://newruntime.com/posts/augment-your-livekit-agent-with-modal-gpus-3c5d04.md","json":"https://newruntime.com/posts/augment-your-livekit-agent-with-modal-gpus-3c5d04.json"}
---

# Augment Your LiveKit Agent with Modal GPUs

## Retrieval answer

Modal published a tutorial showing how to pair LiveKit Agents with custom models hosted on Modal GPUs.

Modal published a tutorial showing how to pair LiveKit Agents with custom models hosted on Modal GPUs. The example builds a video avatar using BitHuman’s open-weights Expression Video Avatar and Qwen3-TTS, then connects it to a LiveKit room.

The setup uses Modal’s Server endpoint to launch the avatar container. Modal says its Sticky Sessions primitive keeps a client associated with the same container after WebSocket reconnections; the LiveKit agent starts the session, calls the `/launch` endpoint with its token, and ends the session when the call finishes.

Modal also says GPU snapshots hide cold starts that would otherwise require loading gigabytes of model weights. The post links to full code and describes the BitHuman integration as a self-hosted GPU container.

The source does not provide latency, throughput, reliability, pricing, or production benchmark results for this configuration. It also does not announce a new LiveKit or Modal product release.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Generative Media](https://newruntime.com/topics/generative-media.md): Explore the generative-media topic hub.
- topic hub: [Multimodal](https://newruntime.com/topics/multimodal.md): Explore the multimodal topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)