Run This Ai
EN DE

CosyVoice

Alibaba's multilingual voice generation and cloning with natural emotion, tone, and accent control

★ 21,898 GitHub Apache-2.0 text-to-speechvoice-cloningttsmultilingualspeech-synthesisalibaba Image & Video

Overview

CosyVoice is Alibaba's open-source multilingual voice generation framework that excels at text-to-speech and voice cloning with natural prosody and emotional expression. Built on a large language model architecture for speech, CosyVoice supports zero-shot voice cloning from just a few seconds of audio, cross-lingual voice generation (speaking a different language with a source voice), and fine-grained control over emotion, speaking rate, and pitch. The framework includes pre-trained models for Mandarin Chinese, English, Japanese, Korean, and more. It offers both streaming and non-streaming inference modes, a REST API server, and easy deployment via Docker. Ideal for voice assistants, content creation, audiobook generation, and multilingual voice applications.

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:
  cosyvoice:
    image: neosun/cosyvoice:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/cosyvoice:/data

Best VPS for CosyVoice →

Related tools

Stable Diffusion WebUI

Generative image models in your browser

ComfyUI

The most powerful and modular diffusion model GUI with a graph/nodes interface for Stable Diffusion

whisper.cpp

High-performance C++ port of OpenAI Whisper for fast local speech recognition

Fooocus

AI image generator focusing on prompts and generating — a Midjourney-like experience offline

Coqui TTS

Open-source deep learning toolkit for text-to-speech, battle-tested in research and production

ChatTTS

High-quality conversational text-to-speech model optimized for natural daily dialogue

Guides & articles

CosyVoice Tutorial — Deploy Voice Cloning with Docker in 10 Minutes

Step-by-step Docker deployment of CosyVoice for multilingual TTS and zero-shot voice cloning with real performance benchmarks.

Jun 30, 2026

CosyVoice Guide — Alibaba's Open-Source Voice Generation That Actually Sounds Human

I spent a week testing CosyVoice — Alibaba's open-source TTS with zero-shot voice cloning, cross-lingual support, and real emotion control. Here's my honest review and deployment guide.

Jun 30, 2026