Run This Ai
EN DE

Speech-to-Speech

Build local voice agents with open-source models

★ 6,237 GitHub Apache-2.0 speechvoiceaudio-agentsopen-sourcehuggingfacelocal-aivoice-agents AI Agents

Overview

Speech-to-Speech by Hugging Face lets you build, customize, and run voice agents entirely on your local hardware using open-source models. Enjoy full privacy, zero API costs, and complete control over your voice AI pipeline — from speech recognition and natural language understanding to speech synthesis. With 6.2K+ GitHub stars and an Apache-2.0 license, this tool integrates with the Hugging Face ecosystem, supports multiple languages, and runs efficiently on consumer GPUs. Perfect for voice assistants, call automation, accessibility tools, and speech AI experimentation.

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

Related tools

Guides & articles