Run This Ai
EN DE

MeloTTS

High-quality multilingual text-to-speech by MyShell.ai — supports English, Spanish, French, Chinese, Japanese, and Korean

★ 7,518 GitHub MIT ttsspeech-synthesismultilingualvoice-cloningaudio Image & Video

Overview

MeloTTS is an open-source, high-quality text-to-speech (TTS) library developed by MyShell.ai. It delivers natural-sounding speech synthesis across six languages: English, Spanish, French, Chinese, Japanese, and Korean, with support for multiple accents including American, British, Indian, and Australian English. Key features include real-time CPU-based inference that runs efficiently without GPU, voice cloning capabilities for custom speaker synthesis, and a clean Python API for seamless integration. The model uses an optimized VITS architecture with prosody control for natural intonation and rhythm. MeloTTS is ideal for content creators, AI voice assistants, accessibility tools, e-learning platforms, and any application requiring high-quality multilingual speech synthesis. Its lightweight design makes it suitable for edge deployment and local inference without cloud dependencies.

Requirements

Min vCPU
2
Min RAM
2048 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
4096 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:
  melotts:
    image: sensejworld/melotts:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/melotts:/data

Best VPS for MeloTTS →

Related tools

Guides & articles