{"name":"ChatTTS: A Generative Speech Model for Natural Dialogue and LLM Assistants","description":"ChatTTS is an advanced text-to-speech model specifically designed for dialogue scenarios, such as those involving LLM assistants. It offers highly natural and expressive speech synthesis, featuring fine-grained control over prosodic elements like laughter, pauses, and interjections. This Python-based project supports both English and Chinese, making it a powerful tool for conversational AI applications.","github":"https://github.com/2noise/ChatTTS","url":"https://osrepos.com/repo/2noise-chattts","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/2noise-chattts","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/2noise-chattts.md","json":"https://osrepos.com/repo/2noise-chattts.json","topics":["chattts","text-to-speech","tts","llm","python","speech synthesis","conversational AI","machine learning"],"keywords":["chattts","text-to-speech","tts","llm","python","speech synthesis","conversational AI","machine learning"],"stars":null,"summary":"ChatTTS is an advanced text-to-speech model specifically designed for dialogue scenarios, such as those involving LLM assistants. It offers highly natural and expressive speech synthesis, featuring fine-grained control over prosodic elements like laughter, pauses, and interjections. This Python-based project supports both English and Chinese, making it a powerful tool for conversational AI applications.","content":"## Introduction\n\nChatTTS is a cutting-edge generative speech model specifically engineered for daily dialogue and conversational scenarios, particularly useful for LLM assistants. This project stands out by delivering highly natural and expressive speech synthesis, making interactions feel more human-like.\n\nKey highlights of ChatTTS include:\n*   **Conversational TTS**: Optimized for dialogue, it enables natural and expressive speech synthesis, supporting multiple speakers for interactive conversations.\n*   **Fine-grained Control**: The model can predict and control detailed prosodic features, such as laughter, pauses, and interjections, adding significant realism.\n*   **Better Prosody**: ChatTTS surpasses many open-source TTS models in terms of prosody, offering pretrained models for further research and development.\n\nCurrently, ChatTTS supports both English and Chinese languages, with more languages planned for future releases.\n\n## Installation\n\nGetting started with ChatTTS is straightforward. You can clone the repository and install dependencies, or install it directly via PyPI.\n\nFirst, clone the repository:\nbash\ngit clone https://github.com/2noise/ChatTTS\ncd ChatTTS\n\n\nThen, install the required packages. You can do this directly or using a conda environment:\n\n**1. Install Directly:**\nbash\npip install --upgrade -r requirements.txt\n\n\n**2. Install from Conda:**\nbash\nconda create -n chattts python=3.11\nconda activate chattts\npip install -r requirements.txt\n\n\nAlternatively, you can install ChatTTS from PyPI or directly from GitHub:\n\n**Install from PyPI (stable version):**\nbash\npip install ChatTTS\n\n\n**Install the latest version from GitHub:**\nbash\npip install git+https://github.com/2noise/ChatTTS\n\n\n## Examples\n\nChatTTS provides various ways to generate speech, from a user-friendly WebUI to command-line inference and direct Python integration.\n\n**Quick Start:**\n\n**1. Launch WebUI:**\nbash\npython examples/web/webui.py\n\n\n**2. Infer by Command Line:**\nbash\npython examples/cmd/run.py \"Your text 1.\" \"Your text 2.\"\n\nThis will save audio to `./output_audio_n.mp3`.\n\n**Basic Usage (Python):**\npython\nimport ChatTTS\nimport torch\nimport torchaudio\n\nchat = ChatTTS.Chat()\nchat.load(compile=False) # Set to True for better performance\n\ntexts = [\"PUT YOUR 1st TEXT HERE\", \"PUT YOUR 2nd TEXT HERE\"]\n\nwavs = chat.infer(texts)\n\nfor i in range(len(wavs)):\n    try:\n        torchaudio.save(f\"basic_output{i}.wav\", torch.from_numpy(wavs[i]).unsqueeze(0), 24000)\n    except:\n        torchaudio.save(f\"basic_output{i}.wav\", torch.from_numpy(wavs[i]), 24000)\n\nFor more advanced control over speaker timbre, temperature, and fine-grained prosodic features like `[laugh]` or `[uv_break]`, refer to the \"Advanced Usage\" section in the official GitHub README.\n\n## Why Use ChatTTS?\n\nChatTTS is an excellent choice for developers and researchers working on conversational AI, virtual assistants, or any application requiring highly natural and expressive speech. Its optimization for dialogue, coupled with fine-grained control over prosody, allows for the creation of truly engaging and lifelike audio experiences. The project's active development, multi-language support, and strong community backing further solidify its position as a leading open-source TTS solution.\n\n## Links\n\n*   **GitHub Repository**: [https://github.com/2noise/ChatTTS](https://github.com/2noise/ChatTTS)\n*   **Hugging Face Models**: [https://huggingface.co/2Noise/ChatTTS](https://huggingface.co/2Noise/ChatTTS)\n*   **Discord Server**: [https://discord.gg/Ud5Jxgx5yD](https://discord.gg/Ud5Jxgx5yD)\n*   **Awesome-ChatTTS (Community Index)**: [https://github.com/libukai/Awesome-ChatTTS/tree/en](https://github.com/libukai/Awesome-ChatTTS/tree/en)","metrics":{"detailViews":9,"githubClicks":11},"dates":{"published":null,"modified":"2025-10-12T16:16:37.000Z"}}