Skip to content
SPECIFICTION
Get listed

CosyVoice

github.com

Free plan LinuxAPISelf-hosted
Visit github.com
Spec score 8.6 #44 of 233 in Text-to-speech tools

Spec sheet

Purpose
CosyVoice is a multilingual text-to-speech system that provides inference, training, and deployment capabilities.Read 3 Oct 2026 · github.com
Platforms
linux,api,self_hostedRead 20 Sep 2026 · github.com
Free plan
YesRead 20 Sep 2026 · github.com
Support
The maintainers direct users to GitHub Issues and an official Dingding chat group for discussion.Read 3 Oct 2026 · github.com
License
The repository is licensed under Apache License 2.0.Read 3 Oct 2026 · github.com
API access
YesRead 20 Sep 2026 · github.com
API interfaces
The deployment instructions include FastAPI and gRPC servers and clients.Read 3 Oct 2026 · github.com
Commercial use
YesRead 20 Sep 2026 · github.com
Deployment options
The repository documents Docker deployment with gRPC or FastAPI, as well as NVIDIA Triton and TensorRT-LLM acceleration.Read 3 Oct 2026 · github.com
Export formats
WAVRead 20 Sep 2026 · github.com
Installation
The repository documents installation with Conda and Python 3.10, and offers pretrained model downloads through ModelScope or Hugging Face.Read 3 Oct 2026 · github.com
Intended use
The repository says its content is for academic purposes and to demonstrate technical capabilities.Read 3 Oct 2026 · github.com
Languages and dialects
Version 3.0 covers nine languages and more than 18 Chinese dialects or accents, with multilingual and cross-lingual zero-shot voice cloning.Read 3 Oct 2026 · github.com
Pronunciation control
The system supports pronunciation inpainting with Chinese Pinyin and English CMU phonemes.Read 3 Oct 2026 · github.com
Runtime requirements
The documented installation uses Python 3.10; the optional ttsfrd normalization wheel is specified for Linux x86_64.Read 3 Oct 2026 · github.com
Streaming
It supports text-in and audio-out streaming, with latency stated as low as 150 ms.Read 3 Oct 2026 · github.com
Text normalization
It supports reading numbers, special symbols, and varied text formats without a traditional frontend module.Read 3 Oct 2026 · github.com
vLLM compatibility
The repository says CosyVoice 2 and 3 support vLLM 0.11.x or newer and vLLM 0.9.0, while versions between those releases are untested.Read 3 Oct 2026 · github.com
Voice cloning
YesRead 20 Sep 2026 · github.com
Voice instructions
Users can provide instructions for language, dialect, emotion, speed, and volume.Read 3 Oct 2026 · github.com
Zero-shot synthesis
Fun-CosyVoice 3.0 is designed for zero-shot multilingual speech synthesis.Read 3 Oct 2026 · github.com

Plans and prices

Open-source software Free The repository provides downloadable source code and models; no paid plans are listed. Apache-2.0 licensed repository · self-managed installation and deployment Read 3 Oct 2026 · github.com

Every CosyVoice plan and price →

Where Specifiction places it

Alternatives to CosyVoiceAll alternatives →