{"data":{"slug":"2noise-chattts","name":"ChatTTS","tagline":"A generative speech model for daily dialogue.","github_url":"https://github.com/2noise/ChatTTS","owner":"2noise","repo":"ChatTTS","owner_avatar_url":"https://avatars.githubusercontent.com/u/164844019?v=4","primary_language":"Python","stars":39850,"forks":4260,"topics":["agent","chat","chatgpt","chattts","chinese","chinese-language","english","english-language","gpt","llm","llm-agent","natural-language-inference","python","text-to-speech","torch","torchaudio","tts"],"archived":false,"github_pushed_at":"2026-04-10T16:33:48+00:00","maintenance_label":"Slowing","stars_delta_30d":82,"url":"https://www.graphcanon.com/tools/2noise-chattts","markdown_url":"https://www.graphcanon.com/tools/2noise-chattts.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/2noise-chattts","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=2noise-chattts","description":"A generative speech model for daily dialogue.","homepage_url":"https://2noise.com","license":"AGPL-3.0","open_issues":60,"watchers":210,"ai_summary":"ChatTTS is a Python-based repository that provides a generative speech model for daily dialogue, supporting both Chinese and English languages. It includes a web interface and command-line inference capabilities.","readme_excerpt":"### Install requirements\n#### 1. Install Directly\n```bash\npip install --upgrade -r requirements.txt\n```\n\n#### 2. Install from conda\n```bash\nconda create -n chattts python=3.11\nconda activate chattts\npip install -r requirements.txt\n```\n\n#### Optional: Install vLLM (Linux only)\n```bash\npip install safetensors vllm==0.2.7 torchaudio\n```\n\n#### Unrecommended Optional: Install TransformerEngine if using NVIDIA GPU (Linux only)\n> [!Warning]\n> DO NOT INSTALL! \n> The adaptation of TransformerEngine is currently under development and CANNOT run properly now. \n> Only install it on developing purpose. See more details on at #672 #676\n\n> [!Note]\n> The installation process is very slow.\n\n```bash\npip install git+https://github.com/NVIDIA/TransformerEngine.git@stable\n```\n\n#### Unrecommended Optional: Install FlashAttention-2 (mainly NVIDIA GPU)\n> [!Warning]\n> DO NOT INSTALL! \n> Currently the FlashAttention-2 will slow down the generating speed according to [this issue](https://github.com/huggingface/transformers/issues/26990). \n> Only install it on developing purpose.\n\n> [!Note]\n> See supported devices at the [Hugging Face Doc](https://huggingface.co/docs/transformers/perf_infer_gpu_one#flashattention-2).\n\n\n```bash\npip install flash-attn --no-build-isolation\n```\n\n---\n\n### Quick Start\n> Make sure you are under the project root directory when you execute these commands below.\n\n#### 1. Launch WebUI\n```bash\npython examples/web/webui.py\n```\n\n#### 2. Infer by Command Line\n> It will save audio to `./output_audio_n.mp3`\n\n```bash\npython examples/cmd/run.py \"Your text 1.\" \"Your text 2.\"\n```\n\n---\n\n## Installation\n\n1. Install the stable version from PyPI\n```bash\npip install ChatTTS\n```\n\n2. Install the latest version from GitHub\n```bash\npip install git+https://github.com/2noise/ChatTTS\n```\n\n3. Install from local directory in dev mode\n```bash\npip install -e .\n```","github_created_at":"2024-05-27T18:26:49+00:00","created_at":"2026-07-07T17:31:31.416643+00:00","updated_at":"2026-09-30T21:19:41.979488+00:00","categories":[{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"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":"agent","name":"agent"},{"slug":"chat","name":"chat"},{"slug":"chatgpt","name":"chatgpt"},{"slug":"chattts","name":"chattts"},{"slug":"chinese-language","name":"chinese-language"},{"slug":"english-language","name":"english-language"},{"slug":"gpt","name":"gpt"},{"slug":"llm-agent","name":"llm-agent"}],"trust":{"provenance":{"is_fork":false,"github_id":806709826,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:39:57.429Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":160,"last_release_at":"2026-04-10T16:33:49Z","stars_delta_30d":82,"open_issues_delta_30d":0},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":72,"high_count":0,"last_scan_at":"2026-09-18T08:39:59.627Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:39:56.301Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-18T08:39:56.301Z"},"license_spdx":{"value":"AGPL-3.0","source":"github.license","observed_at":"2026-09-18T08:39:56.301Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Optional installations like vLLM and TransformerEngine are available but come with specific warnings and limitations."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["When you need a tool that supports both Chinese and English for daily dialogue generation.","If you require a web interface for easier interaction with the speech model.","For command-line inference capabilities, allowing for script-based audio generation.","When you are working in a Linux environment and want to experiment with optional installations like vLLM."],"when_not_to_use":["If you are working on a project that requires the use of TransformerEngine with NVIDIA GPU, as it is currently under development and cannot run properly.","When you need fast text-to-speech generation, as the optional installation of FlashAttention-2 can slow down the generating speed.","If you are not comfortable with a slow installation process, as noted in the repository documentation."],"source":"enrich:decision_facts","observed_at":"2026-09-18T11:42:28.198Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Optional installations like vLLM and TransformerEngine are available but come with specific warnings and limitations."},{"label":"Adopt for","value":"ChatTTS is a Python-based generative speech model for daily dialogue, supporting both Chinese and English languages. It offers a web interface and command-line inference capabilities."},{"label":"License detail","value":"AGPL-3.0"}]}}