{"data":{"slug":"openmoss-moss-tts","name":"MOSS-TTS","tagline":"An open-source speech and sound generation model family designed for high-fidelity scenarios including multi-speaker dialogue。","github_url":"https://github.com/OpenMOSS/MOSS-TTS","owner":"OpenMOSS","repo":"MOSS-TTS","owner_avatar_url":"https://avatars.githubusercontent.com/u/156300419?v=4","primary_language":"Python","stars":4119,"forks":373,"topics":["audio","audio-tokenizer","llm","multilingual","multimodal","speech-synthesis","streaming","text-to-audio","text-to-speech","tts","voice-cloning"],"archived":false,"github_pushed_at":"2026-09-06T06:19:28+00:00","maintenance_label":"Active","stars_delta_30d":197,"url":"https://www.graphcanon.com/tools/openmoss-moss-tts","markdown_url":"https://www.graphcanon.com/tools/openmoss-moss-tts.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openmoss-moss-tts","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openmoss-moss-tts","description":"An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS","homepage_url":"https://mosi.cn/models/moss-tts","license":"Apache-2.0","open_issues":19,"watchers":21,"ai_summary":"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.","readme_excerpt":"# Install uv first: https://docs.astral.sh/uv/getting-started/installation/\ngit clone https://github.com/OpenMOSS/MOSS-TTS.git\ncd MOSS-TTS\nuv venv --python 3.12 .venv\nsource .venv/bin/activate\nuv pip install --torch-backend cu128 -e \".[torch-runtime]\"\n```\n\n#### (Optional) Install FlashAttention 2\n\nFor better speed and lower GPU memory usage, you can install FlashAttention 2 if your hardware supports it.\n\nIf you use Conda/pip:\n\n```bash\npip install --extra-index-url https://download.pytorch.org/whl/cu128 -e \".[torch-runtime,flash-attn]\"\n```\n\nIf your machine has limited RAM and many CPU cores, you can cap build parallelism:\n\n```bash\nMAX_JOBS=4 pip install --extra-index-url https://download.pytorch.org/whl/cu128 -e \".[torch-runtime,flash-attn]\"\n```\n\nIf you use `uv`:\n\n```bash\nuv pip install --torch-backend cu128 -e \".[torch-runtime,flash-attn]\"\n```\n\nIf your machine has limited RAM and many CPU cores, you can cap build parallelism:\n\n```bash\nMAX_JOBS=4 uv pip install --torch-backend cu128 -e \".[torch-runtime,flash-attn]\"\n```\n\nNotes:\n- Dependencies are managed in `pyproject.toml`, which currently pins `torch==2.9.1+cu128` and `torchaudio==2.9.1+cu128`.\n- In `uv`, `--torch-backend cu128` lets uv fetch compatible PyTorch CUDA wheels and resolve the rest from PyPI with the default safe index strategy.\n- If you need another backend, replace `cu128` with your target (for example, `cpu`, `cu126`).\n- If FlashAttention 2 fails to build on your machine, you can skip it and use the default attention backend.\n- FlashAttention 2 is only available on supported GPUs and is typically used with `torch.float16` or `torch.bfloat16`.\n\n\n<a id=\"moss-tts-basic-usage\"></a>\n\n---\n\n# 1. Install (torch-free)\npip install -e \".[llama-cpp-onnx]\"\n\n---\n\n### Installation Profiles\n\n| Profile | Install Command | Dependencies | Use Case |\n|---------|----------------|--------------|----------|\n| **Torch-free (ONNX)** | `pip install -e \".[llama-cpp-onnx]\"` | numpy, onnxruntime-gpu, tokenizers | Recommended starting point |\n| **Torch-free (TRT)** | `pip install -e \".[llama-cpp-trt]\"` | numpy, tensorrt, cuda-python | Maximum audio tokenizer speed (build engines yourself) |\n| **Torch-accelerated** | `pip install -e \".[llama-cpp-onnx,llama-cpp-torch]\"` | + torch | GPU-accelerated LM heads (~30x faster) |\n\n> **Want to convert weights yourself?** See the [conversion guide](moss_tts_delay/llama_cpp/conversion/README.md) for step-by-step instructions on extracting, converting, and quantizing MOSS-TTS weights with llama.cpp.\n\n---\n\n## LICENSE\n\nModels in MOSS-TTS Family are licensed under the Apache License 2.0.","github_created_at":"2026-02-07T14:05:49+00:00","created_at":"2026-07-11T12:07:38.17234+00:00","updated_at":"2026-09-20T07:07:12.415175+00:00","categories":[{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"audio","name":"audio"},{"slug":"llm","name":"llm"},{"slug":"multimodal","name":"multimodal"},{"slug":"text-to-speech","name":"text-to-speech"},{"slug":"voice-cloning","name":"voice-cloning"}],"trust":{"provenance":{"is_fork":false,"github_id":1152193330,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T07:07:09.720Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":0,"days_since_push":14,"last_release_at":null,"stars_delta_30d":197,"open_issues_delta_30d":6},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:07:46.739Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T07:07:10.942Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-20T07:07:10.942Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T07:07:10.942Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T07:07:10.942Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Free to use under the Apache License, version 2.0."},"requirements":{"min_ram_gb":null,"requires_docker":false},"constraints":{"persona":"developer_harness","min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"when_to_use":["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."],"when_not_to_use":["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."],"source":"enrich:decision_facts","observed_at":"2026-07-17T00:10:53.333Z"},"constraint_facets":{"persona":"developer_harness","min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - Free to use under the Apache License, version 2.0."},{"label":"Adopt for","value":"MOSS-TTS, an open-source project for generating high-fidelity audio including speech and sound effects, supports real-time TTS and voice design tasks."},{"label":"License detail","value":"Apache-2.0"},{"label":"Persona","value":"developer harness"}]}}