Home/LLM Frameworks/MOSS-TTS

MOSS-TTS

Enrichment pending

OpenMOSS/MOSS-TTS

GitHub Website

GraphCanon updated today · GitHub synced today

3.8k

Stars

330

Forks

Open issues

Watchers

Last push

Python Apache-2.0Created Feb 7, 2026

Trust & integrity

Full report

Maintenance: Active (19d since push); As of today · Source: github_public_v1
Provenance: Not a fork · Organization account; As of today · Source: github_public_v1
Security (OSV): No lockfile; As of today · Source: none

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

Overview

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.

Capability facts

CLI: CLI entrypoint
Source: pyproject.toml:[project.scripts] · Jul 11, 2026
Languages: python
Source: github.language+pyproject.toml · Jul 11, 2026

Compatibility

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

Python runtimePython

Source: README excerpt (regex_v1, Jul 11, 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.