MOSS-TTS

An open-source speech and sound generation model family designed for high-fidelity scenarios including multi-speaker dialogue。

GitHub Website

GraphCanon updated 3w · GitHub synced 3w

3.9k stars350 forksLast push 3w Python Apache-2.0

Decision brief

MOSS-TTS, an open-source project for generating high-fidelity audio including speech and sound effects, supports real-time TTS and voice design tasks.

Good fit when

When developing applications that require complex, high-expressiveness audio scenarios, such as long-form speech or multi-speaker dialogues.
For projects aiming to produce environmental sound effects along with synthetic speech within real-time constraints, thanks to its support for real-time TTS.

Avoid when

If your project requires minimal dependencies and simple installation processes since MOSS-TTS involves setting up a virtual environment and specific PyTorch versions.
When working on systems with limited GPU capabilities, because MOSS-TTS benefits from but may require certain GPUs for FlashAttention 2 optimizations.

Pricing:: freemium - Free to use under the Apache License, version 2.0.

Observed Jul 17, 2026 · Source: enrich:decision_facts

MOSS-TTS alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Very active (3d since push); As of 3w
Provenance: Not a fork · Organization account; As of 3w
Security (OSV): No lockfile; As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install MOSS-TTS

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

VoxCPM

Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

34k★

EmotiVoice

A Multi-Voice and Prompt-Controlled TTS Engine

8.5k★

silero-models

Silero Models provide simple access to pre-trained text-to-speech models

6.0k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

MOSS-TTS Family is an open-source project from MOSI.AI and the OpenMOSS team focused on generating high-quality, expressive audio, covering areas such as long-form speech, voice design, and real-time TTS.

Capability facts

CLI: CLI entrypoint
Source: pyproject.toml:[project.scripts] · Jul 29, 2026
Languages: python
Source: github.language+pyproject.toml · Jul 29, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Jul 29, 2026)

uv venv --python 3.12 .venv

Source link

README

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:

```bash
pip install --extra-index-url https://download.pytorch.org/whl/cu128 -e ".[torch-runtime,flash-attn]"

If your machine has limited RAM and many CPU cores, you can cap build parallelism:

MAX_JOBS=4 pip install --extra-index-url https://download.pytorch.org/whl/cu128 -e ".[torch-runtime,flash-attn]"

If you use uv:

uv pip install --torch-backend cu128 -e ".[torch-runtime,flash-attn]"

If your machine has limited RAM and many CPU cores, you can cap build parallelism:

MAX_JOBS=4 uv pip install --torch-backend cu128 -e ".[torch-runtime,flash-attn]"

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.

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.

LICENSE

Models in MOSS-TTS Family are licensed under the Apache License 2.0.

For agents

This page has a .md twin and JSON over the API.

/tools/openmoss-moss-tts.md GET /api/graphcanon/tools/openmoss-moss-tts GET /api/graphcanon/graph?tool=openmoss-moss-tts