{"name":"Spark-TTS: Efficient LLM-Based Text-to-Speech with Zero-Shot Voice Cloning","description":"Spark-TTS is an advanced text-to-speech system that leverages large language models (LLM) for highly accurate and natural-sounding voice synthesis. Built on Qwen2.5, it offers streamlined efficiency, high-quality zero-shot voice cloning, bilingual support for Chinese and English, and controllable speech generation, making it versatile for both research and production.","github":"https://github.com/SparkAudio/Spark-TTS","url":"https://osrepos.com/repo/sparkaudio-spark-tts","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/sparkaudio-spark-tts","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/sparkaudio-spark-tts.md","json":"https://osrepos.com/repo/sparkaudio-spark-tts.json","topics":["Python","Text-to-Speech","LLM","Voice Cloning","AI","Speech Synthesis","Machine Learning","Deep Learning"],"keywords":["Python","Text-to-Speech","LLM","Voice Cloning","AI","Speech Synthesis","Machine Learning","Deep Learning"],"stars":null,"summary":"Spark-TTS is an advanced text-to-speech system that leverages large language models (LLM) for highly accurate and natural-sounding voice synthesis. Built on Qwen2.5, it offers streamlined efficiency, high-quality zero-shot voice cloning, bilingual support for Chinese and English, and controllable speech generation, making it versatile for both research and production.","content":"## Introduction\nSpark-TTS is an advanced text-to-speech (TTS) system developed by SparkAudio, designed for highly accurate and natural-sounding voice synthesis. This repository provides the official PyTorch inference code for the model, which leverages the power of large language models (LLM) to deliver efficient and flexible speech generation. Spark-TTS stands out by building entirely on Qwen2.5, simplifying the process by directly reconstructing audio from LLM-predicted codes, thus enhancing efficiency and reducing complexity.\n\nKey features of Spark-TTS include:\n\n*   **Simplicity and Efficiency**: Built entirely on Qwen2.5, Spark-TTS eliminates the need for additional generation models like flow matching. It directly reconstructs audio from LLM-predicted codes, streamlining the process and improving efficiency.\n*   **High-Quality Zero-Shot Voice Cloning**: Supports zero-shot voice cloning, allowing it to replicate a speaker's voice without specific training data. This is ideal for cross-lingual and code-switching scenarios.\n*   **Bilingual Support**: Seamlessly synthesizes speech in both Chinese and English, with capabilities for zero-shot voice cloning across languages.\n*   **Controllable Speech Generation**: Enables the creation of virtual speakers by adjusting parameters such as gender, pitch, and speaking rate.\n\nThe project's paper, \"Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens\", was recently published, highlighting its innovative approach.\n\n## Installation\nGetting Spark-TTS up and running is straightforward. Follow these steps to set up the environment and download the necessary models.\n\n### 1. Clone the Repository\nsh\ngit clone https://github.com/SparkAudio/Spark-TTS.git\ncd Spark-TTS\n\n\n### 2. Create Conda Environment and Install Dependencies\nEnsure you have Conda installed. For installation instructions, refer to the [Miniconda installation guide](https://docs.conda.io/en/latest/miniconda.html).\n\nsh\nconda create -n sparktts -y python=3.12\nconda activate sparktts\npip install -r requirements.txt\n# For users in mainland China, you can use a mirror:\n# pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com\n\nFor Windows installation, refer to the [Windows Installation Guide](https://github.com/SparkAudio/Spark-TTS/issues/5).\n\n### 3. Download Pre-trained Models\n\n**Via Python:**\npython\nfrom huggingface_hub import snapshot_download\n\nsnapshot_download(\"SparkAudio/Spark-TTS-0.5B\", local_dir=\"pretrained_models/Spark-TTS-0.5B\")\n\n\n**Via Git LFS:**\nsh\nmkdir -p pretrained_models\n\n# Make sure you have git-lfs installed (https://git-lfs.com)\ngit lfs install\n\ngit clone https://huggingface.co/SparkAudio/Spark-TTS-0.5B pretrained_models/Spark-TTS-0.5B\n\n\n## Examples\nSpark-TTS offers both command-line interface (CLI) and a user-friendly web interface for inference.\n\n### Basic CLI Usage\nRun the provided demo script:\nsh\ncd example\nbash infer.sh\n\n\nAlternatively, you can directly execute the following command in the command line to perform inference:\n\nsh\npython -m cli.inference \\\n    --text \"text to synthesis.\" \\\n    --device 0 \\\n    --save_dir \"path/to/save/audio\" \\\n    --model_dir pretrained_models/Spark-TTS-0.5B \\\n    --prompt_text \"transcript of the prompt audio\" \\\n    --prompt_speech_path \"path/to/prompt_audio\"\n\n\n### Web UI Usage\nYou can start the UI interface by running `python webui.py --device 0`, which allows you to perform Voice Cloning and Voice Creation. Voice Cloning supports uploading reference audio or directly recording the audio.\n\n### Demos\nExperience the high-quality zero-shot voice cloning capabilities of Spark-TTS by visiting the [official demo page](https://sparkaudio.github.io/spark-tts/). You can hear examples of various voices, including public figures and fictional characters, in both English and Chinese.\n\n## Why Use Spark-TTS\nSpark-TTS represents a significant advancement in text-to-speech technology, offering a powerful and efficient solution for generating natural-sounding speech. Its LLM-based architecture, built on Qwen2.5, simplifies the synthesis pipeline while delivering exceptional results. With features like zero-shot voice cloning, comprehensive bilingual support, and fine-grained control over speech characteristics, Spark-TTS is an invaluable tool for researchers, developers, and anyone looking to integrate cutting-edge TTS capabilities into their projects. Whether for personalized speech synthesis, assistive technologies, or linguistic research, Spark-TTS provides a robust and versatile platform.\n\n## Links\nExplore Spark-TTS further through these official resources:\n\n*   [GitHub Repository](https://github.com/SparkAudio/Spark-TTS)\n*   [Paper on ArXiv](https://arxiv.org/pdf/2503.01710)\n*   [Official Demo Page](https://sparkaudio.github.io/spark-tts/)\n*   [Hugging Face Model Page](https://huggingface.co/SparkAudio/Spark-TTS-0.5B)\n*   [Windows Installation Guide](https://github.com/SparkAudio/Spark-TTS/issues/5)\n*   [Miniconda Installation Guide](https://docs.conda.io/en/latest/miniconda.html)\n*   [Git LFS Installation Guide](https://git-lfs.com)","metrics":{"detailViews":3,"githubClicks":14},"dates":{"published":null,"modified":"2026-04-05T20:06:22.000Z"}}