Ultravox
Open-source multimodal LLM for real-time voice AI — text in, speech out with ultra-low latency.
Overview
Requirements
Recommended VPS
Hostinger · KVM 4
4 vCPU · 16384 MB · 200 GB
Hostinger · KVM 4
4 vCPU · 16384 MB · 200 GB
Hostinger · KVM 8
8 vCPU · 32256 MB · 400 GB
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
Related tools
ebook2audiobook
Generate audiobooks from e-books with voice cloning and 1158+ languages.
FunASR
End-to-end speech recognition toolkit with streaming ASR, VAD, punctuation, and speaker diarization
DIA
Ultra-realistic dialogue TTS in one pass
NeMo Speech
NVIDIA scalable generative AI framework for speech — ASR, TTS, and speech language models in one toolkit.
Supertonic
Lightning-fast, on-device, multilingual TTS running natively via ONNX.
Piper
Fast, local neural text-to-speech that runs fully offline
Guides & articles
How to Self-Host Ultravox with Docker: Step-by-Step Tutorial
Run Ultravox, the real-time voice LLM, on your own hardware. Full Docker and Docker Compose setup, requirements, and a hands-on review.
Ultravox: The Open-Source Voice LLM for Real-Time AI Conversations
Ultravox is a fast open-source multimodal LLM that turns text into natural speech directly — no separate TTS pipeline. Learn why it is the best choice for real-time voice AI.