Run This Ai
EN DE

Ultravox

Open-source multimodal LLM for real-time voice AI — text in, speech out with ultra-low latency.

★ 4,556 GitHub MIT realtime-voicemultimodal-llmspeechvoice-agentsself-hosted Speech & Audio

Overview

Open-source multimodal LLM for real-time voice AI — text in, speech out with ultra-low latency. Built by Fixie AI, Ultravox generates natural speech directly from text input, eliminating separate speech-to-text and text-to-speech pipelines. Fully self-hostable with Docker for voice agents, telephony assistants, and real-time conversational interfaces with full data control.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8192 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  ultravox:
    image: ghcr.io/fixie-ai/ultravox:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/ultravox:/data

Best VPS for Ultravox →

Related tools

Guides & articles