MOSS-TTS — AI 语音合成工具中文文档
AI Skill Hub 强烈推荐：MOSS-TTS — AI 语音合成工具中文文档 是一款优质的AI工具。已获得 1.9k 颗 GitHub Star，AI 综合评分 8.6 分，在同类工具中表现稳健。如果你正在寻找可靠的AI工具解决方案，这是一个值得深入了解的选择。
**为什么要使用开源工具而非商业 SaaS？**
对于个人开发者和有隐私需求的用户，本地部署的开源工具意味着数据不离本机，不受第三方服务商的数据政策约束。同时，开源工具通常没有使用次数限制和月度费用，一次安装即可长期使用，对于高频使用场景的总拥有成本（TCO）远低于订阅制商业工具。
**安装与环境准备**
MOSS-TTS — AI 语音合成工具中文文档 依赖 Python 运行环境。建议通过 pyenv（Python）或 nvm（Node.js）管理 Python 版本，避免全局环境污染。对于新手用户，推荐先创建虚拟环境（python -m venv venv && source venv/bin/activate），再安装依赖，这样即使出现问题也可以随时删除虚拟环境重新开始，不影响系统稳定性。
**社区与维护**
GitHub Issue 和 Discussion 是获取帮助的最快渠道。在提问前建议先检查 Closed Issues（已关闭的问题），大多数常见问题都已有解答。遇到 Bug 时，提供 pip list 的输出、完整错误堆栈和最小可复现示例，能显著提高开发者响应速度。AI Skill Hub 将持续追踪 MOSS-TTS — AI 语音合成工具中文文档 的版本更新，及时通知重要功能变化。
MOSS-TTS — AI 语音合成工具中文文档 是一款基于 Python 开发的开源工具，专注于 audio、audio-tokenizer、llm 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
MOSS-TTS — AI 语音合成工具中文文档 是一款基于 Python 开发的开源工具，专注于 audio、audio-tokenizer、llm 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
# 方式一：pip 安装（推荐）
pip install moss-tts
# 方式二：虚拟环境安装（推荐生产环境）
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install moss-tts
# 方式三：从源码安装（获取最新功能）
git clone https://github.com/OpenMOSS/MOSS-TTS
cd MOSS-TTS
pip install -e .
# 验证安装
python -c "import moss_tts; print('安装成功')"
- 访问 GitHub 仓库页面
- 按照 README 文档完成依赖安装
- 根据系统环境完成初始化配置
- 参考官方示例或文档开始使用
- 遇到问题可在 GitHub Issues 中查找解答
# 命令行使用
moss-tts --help
# 基本用法
moss-tts input_file -o output_file
# Python 代码中调用
import moss_tts
# 示例
result = moss_tts.process("input")
print(result)
# moss-tts 配置文件示例（config.yml） app: name: "moss-tts" debug: false log_level: "INFO" # 运行时指定配置文件 moss-tts --config config.yml # 或通过环境变量配置 export MOSS_TTS_API_KEY="your-key" export MOSS_TTS_OUTPUT_DIR="./output"
MOSS-TTS Family
<br>
<p align="center"> <img src="./assets/OpenMOSS_Logo.png" height="70" align="middle" /> <img src="./assets/mosi-logo.png" height="50" align="middle" /> </p>
<a href="https://studio.mosi.cn"><img src="https://img.shields.io/badge/AIStudio-Try-green?logo=internet-explorer&"></a> <a href="https://studio.mosi.cn/docs/moss-tts"><img src="https://img.shields.io/badge/API-Docs-00A3FF?logo=fastapi&"></a> <a href="https://x.com/Open_MOSS"><img src="https://img.shields.io/badge/Twitter-Follow-black?logo=x&"></a> <a href="https://discord.gg/Xf3aXddCjc"><img src="https://img.shields.io/badge/Discord-Join-5865F2?logo=discord&"></a> <a href="./assets/wechat.jpg"><img src="https://img.shields.io/badge/WeChat-Join-07C160?logo=wechat&logoColor=white" alt="WeChat"></a> </div>
MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental sound effects, and real‑time streaming TTS.
Introduction
<p align="center"> <img src="./assets/moss_tts_family.jpeg" width="85%" /> </p>
When a single piece of audio needs to sound like a real person, pronounce every word accurately, switch speaking styles across content, remain stable over tens of minutes, and support dialogue, role‑play, and real‑time interaction, a single TTS model is often not enough. The MOSS‑TTS Family breaks the workflow into five production‑ready models that can be used independently or composed into a complete pipeline.
- MOSS‑TTS: The flagship production model featuring high fidelity and optimal zero-shot voice cloning. It supports long-speech generation, fine-grained control over Pinyin, phonemes, and duration, as well as multilingual/code-switched synthesis.
- MOSS‑TTSD: A spoken dialogue generation model for expressive, multi-speaker, and ultra-long dialogues. The new v1.0 version achieves industry-leading performance on objective metrics and outperformed top closed-source models like Doubao and Gemini 2.5-pro in subjective evaluations. You can visit the MOSS-TTSD repository for details.
- MOSS‑VoiceGenerator: An open-source voice design model capable of generating diverse voices and styles directly from text prompts, without any reference speech. It unifies voice design, style control, and synthesis, functioning independently or as a design layer for downstream TTS. Its performance surpasses other top-tier voice design models in arena ratings.
- MOSS‑TTS‑Realtime: A multi-turn context-aware model for real-time voice agents. It uses incremental synthesis to ensure natural and coherent replies, making it ideal for building low-latency voice agents when paired with text models. The TTFB (Time To First Byte) of MOSS-TTS-Realtime reaches 180 ms, and the $T_{\text{LLM-first-sentence}} + T_{\text{MOSS-TTS-Realtime-TTFB}}$ is 377 ms.
- MOSS‑SoundEffect: A content creation model specialized in sound effect generation with wide category coverage and controllable duration. It generates audio for natural environments, urban scenes, biological sounds, human actions, and musical fragments, suitable for film, games, and interactive experiences.
Introduction
MOSS-TTS-Nano is our lightweight TTS model designed for CPU-first realtime deployment. It focuses on the part of speech generation that matters most in practical products: a small footprint, low-latency streaming generation, and voice-cloning quality that is strong enough for local demos, web services, and lightweight production integration. Built on a pure autoregressive Audio Tokenizer + LLM pipeline, it keeps the deployment stack simple while making realtime speech generation accessible even without a GPU.
Its main features include:
- 0.1B parameters: a compact model size that keeps memory usage and deployment cost low, making local deployment and lightweight serving much easier.
- Realtime generation on just 4 CPU cores: streaming speech generation can run efficiently on CPU-only environments, which is practical for local applications and cost-sensitive deployment scenarios.
- Multilingual voice cloning: supports multilingual voice cloning workflows, making it suitable for cross-language synthesis with a single reference speaker.
- 48 kHz stereo input/output: natively supports high-quality stereo audio, improving both reference-audio fidelity and final listening quality.
To learn more about setup, advanced usage, and evaluation metrics, please visit the MOSS-TTS-Nano repository.
<p align="center">Architecture of MOSS-TTS-Nano</p>
<a id="moss-tts-nano-model-weights"></a>
Introduction
MOSS-Audio-Tokenizer serves as the unified discrete audio interface for the entire MOSS-TTS Family. It is based on the Cat (Causal Audio Tokenizer with Transformer) architecture—a 1.6-billion-parameter, "CNN-free" homogeneous audio tokenizer built entirely from Causal Transformer blocks.
- Unified Discrete Bridge: It acts as the shared backbone for MOSS-TTS, MOSS-TTSD, MOSS-VoiceGenerator, MOSS-SoundEffect, and MOSS-TTS-Realtime, providing a consistent audio representation across the family.
- Extreme Compression & High Fidelity: It compresses 24kHz raw audio into a remarkably low frame rate of 12.5Hz. Utilizing a 32-layer Residual Vector Quantizer (RVQ), it supports high-fidelity reconstruction across variable bitrates from 0.125kbps to 4kbps.
- Massive-Scale General Audio Training: Trained from scratch on 3 million hours of diverse data (speech, sound effects, and music), the model achieves state-of-the-art reconstruction among open source audio tokenizers.
- Native Streaming Design: The pure Causal Transformer architecture is specifically designed for scalability and low-latency streaming inference, enabling real-time production workflows.
To learn more about setup, advanced usage, and evaluation metrics, please visit the MOSS-Audio-Tokenizer Repository
<p align="center"> <img src="./assets/arch_moss_audio_tokenizer.png" alt="MOSS Audio Tokenizer architecture" width="100%" /> Architecture of MOSS Audio Tokenizer </p>
4. Build the C bridge (one-time, requires llama.cpp compiled from source)
cd moss_tts_delay/llama_cpp && bash build_bridge.sh /path/to/llama.cpp && cd ../..
Environment Setup
We recommend a clean, isolated Python environment with Transformers 5.0.0 to avoid dependency conflicts.
Using Conda
conda create -n moss-tts python=3.12 -y
conda activate moss-ttsInstall all required dependencies:
git clone https://github.com/OpenMOSS/MOSS-TTS.git
cd MOSS-TTS
pip install --extra-index-url https://download.pytorch.org/whl/cu128 -e ".[torch-runtime]"Using uv
```bash
Install uv first: https://docs.astral.sh/uv/getting-started/installation/
git clone https://github.com/OpenMOSS/MOSS-TTS.git cd MOSS-TTS uv venv --python 3.12 .venv source .venv/bin/activate uv pip install --torch-backend cu128 -e ".[torch-runtime]"
#### (Optional) Install FlashAttention 2
For better speed and lower GPU memory usage, you can install FlashAttention 2 if your hardware supports it.
If you use Conda/pip:
If your machine has limited RAM and many CPU cores, you can cap build parallelism:
If you use `uv`:
If your machine has limited RAM and many CPU cores, you can cap build parallelism:
Notes: - Dependencies are managed in pyproject.toml, which currently pins torch==2.9.1+cu128 and torchaudio==2.9.1+cu128. - In uv, --torch-backend cu128 lets uv fetch compatible PyTorch CUDA wheels and resolve the rest from PyPI with the default safe index strategy. - If you need another backend, replace cu128 with your target (for example, cpu, cu126). - If FlashAttention 2 fails to build on your machine, you can skip it and use the default attention backend. - FlashAttention 2 is only available on supported GPUs and is typically used with torch.float16 or torch.bfloat16.
<a id="moss-tts-basic-usage"></a>
1. Install (torch-free)
pip install -e ".[llama-cpp-onnx]"
Installation Profiles
| Profile | Install Command | Dependencies | Use Case |
|---|---|---|---|
| **Torch-free (ONNX)** | pip install -e ".[llama-cpp-onnx]" | numpy, onnxruntime-gpu, tokenizers | Recommended starting point |
| **Torch-free (TRT)** | pip install -e ".[llama-cpp-trt]" | numpy, tensorrt, cuda-python | Maximum audio tokenizer speed (build engines yourself) |
| **Torch-accelerated** | pip install -e ".[llama-cpp-onnx,llama-cpp-torch]" | + torch | GPU-accelerated LM heads (~30x faster) |
Want to convert weights yourself? See the conversion guide for step-by-step instructions on extracting, converting, and quantizing MOSS-TTS weights with llama.cpp.
2. Install SGLang
pip install -e ./sglang/python[all]
Quickstart
MOSS‑TTS Basic Usage
If you prefer Gradio demos, we provide 4 scripts for the main models:
| Model | Script | Run |
|---|---|---|
| MOSS-TTS | [clis/moss_tts_app.py](clis/moss_tts_app.py) |
For the MOSS-TTS-Realtime Gradio demo, please refer to MOSS-TTS-Realtime Model Card
```python from pathlib import Path import importlib.util import torch import torchaudio from transformers import AutoModel, AutoProcessor
Quick Start
```bash
Quick Start
```bash
Demo
6. (Optional) Low-memory mode for 8 GB GPUs — loads/unloads components per stage
python -m moss_tts_delay.llama_cpp \ --config configs/llama_cpp/trt-8gb.yaml \ --text "Hello, world!" --output output.wav ```
Configuration
Four pre-built configs are provided in configs/llama_cpp/:
default.yaml— ONNX audio + GGUF backbone (recommended start)trt.yaml— TensorRT audio + GGUF backbone (max throughput, user-built engines)trt-8gb.yaml— Low-memory mode for 8 GB GPUs (staged loading, TRT audio)cpu-only.yaml— fully CPU-based (no GPU required)
Key config options: - heads_backend: auto | numpy | torch — LM heads computation backend - audio_backend: onnx | trt | torch — audio tokenizer backend - low_memory: true | false — staged loading for limited VRAM (loads/unloads encoder, backbone, decoder per stage) - kv_cache_type_k / kv_cache_type_v — KV cache quantization (e.g. q8_0, q4_0) to reduce VRAM - flash_attn: auto | enabled | disabled — flash attention for lower peak VRAM during prefill
For full documentation, see moss_tts_delay/llama_cpp/README.md.
3. (Optional) Fix the SGLang CuDNN compatibility error
OpenClaw API Skills
We add MOSS-TTS skills in ClawHub of 🦞 OpenClaw. You can get your API key from MOSI AI Studio.
| Skill | Description | Install |
|---|---|---|
[feishu-voice-tts](https://clawhub.ai/helloeveryworlds/feishu-voice-tts) | Send voice messages in Feishu | clawhub install feishu-voice-tts |
[moss-tts-voice](https://clawhub.ai/luogao2333/moss-tts-voice) | Call MOSS-TTS API to generate speech | clawhub install moss-tts-voice |
- 构建多智能体协作系统的 Agent 开发者
- 构建企业知识库 / RAG 检索应用的团队
- 做语音类 AI 产品的开发者
- 本地部署优先选 GGUF 量化模型，节省显存并保持响应速度
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- 显存不足直接 OOM — 优先降低 context 或换更小的量化模型
- Python 依赖冲突：建议用 venv / uv 隔离环境
- CLI：直接 npm install -g / pip install，命令行调用
- 本地部署：CPU 8GB 起，GPU 推荐 16GB+ 显存
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
- +Apache-2.0 协议，可免费商用
- +完全开源免费，无授权费用
- +本地部署，数据完全自主可控
- +开发者社区支持，遇问题可查可问
- −安装和初始配置可能需要一定技术基础
- −功能完整性通常不如成熟商业产品
- −技术支持主要依赖开源社区，响应速度不稳定
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议，可商用，需保留版权声明和 NOTICE 文件，含专利授权条款。
总体来看，MOSS-TTS — AI 语音合成工具中文文档 是一款质量优秀的AI工具，在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态，建议收藏备用，结合自身场景选择合适时机引入使用。
| 原始名称 | MOSS-TTS |
| 原始描述 | MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental soun… |
| Topics | audioaudio-tokenizerllmmultimodaltext-to-speechvoice-cloningtts |
| GitHub | https://github.com/OpenMOSS/MOSS-TTS |
| License | Apache-2.0 |
| 语言 | Python |
收录时间：2026-05-22 · 更新时间：2026-05-22 · License：Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。