{"id":25236821,"url":"https://github.com/manascb1344/zonos-api","last_synced_at":"2025-10-16T06:28:26.932Z","repository":{"id":276865087,"uuid":"930561692","full_name":"manascb1344/zonos-api","owner":"manascb1344","description":"Production-ready FastAPI wrapper for Zonos TTS models with GPU acceleration, voice cloning, and emotion control. Supports both Transformer and Hybrid variants. ⚠️ UNSTABLE API - INITIAL RELEASE","archived":false,"fork":false,"pushed_at":"2025-02-22T19:08:03.000Z","size":48,"stargazers_count":26,"open_issues_count":2,"forks_count":4,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-02-22T19:20:19.988Z","etag":null,"topics":["ai","api","docker","fastapi","python","text-to-speech","tts","zonos","zyphra"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/manascb1344.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-02-10T20:44:52.000Z","updated_at":"2025-02-18T14:21:56.000Z","dependencies_parsed_at":null,"dependency_job_id":"b3a69fcb-b807-4dba-9e1e-02867545810f","html_url":"https://github.com/manascb1344/zonos-api","commit_stats":null,"previous_names":["manascb1344/zonos-api"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manascb1344%2Fzonos-api","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manascb1344%2Fzonos-api/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manascb1344%2Fzonos-api/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manascb1344%2Fzonos-api/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/manascb1344","download_url":"https://codeload.github.com/manascb1344/zonos-api/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247378139,"owners_count":20929297,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","api","docker","fastapi","python","text-to-speech","tts","zonos","zyphra"],"created_at":"2025-02-11T15:32:08.266Z","updated_at":"2025-10-16T06:28:21.882Z","avatar_url":"https://github.com/manascb1344.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Zonos API\n\n\u003e ⚠️ **WARNING: UNSTABLE API - INITIAL RELEASE** ⚠️\n\u003e \n\u003e This API is currently in its initial release phase (v1.0.0) and is considered unstable.\n\u003e Breaking changes may occur without notice. Use in production at your own risk.\n\u003e For development and testing purposes only.\n\nA production-grade FastAPI implementation of the Zonos Text-to-Speech model.\n\n## Credits\n\nThis API is built on top of the [Zonos-v0.1-hybrid](https://huggingface.co/Zyphra/Zonos-v0.1-hybrid) and [Zonos-v0.1-transformer](https://huggingface.co/Zyphra/Zonos-v0.1-transformer) models created by [Zyphra](https://huggingface.co/Zyphra). The models feature:\n\n- Zero-shot TTS with voice cloning capabilities\n- Support for multiple languages (100+ languages via eSpeak-ng)\n- High-quality 44kHz audio output\n- Fine-grained control over speaking rate, pitch, audio quality, and emotions\n- Real-time performance (~2x real-time on RTX 4090)\n\nFor more information, visit the model cards on Hugging Face: [Hybrid](https://huggingface.co/Zyphra/Zonos-v0.1-hybrid) | [Transformer](https://huggingface.co/Zyphra/Zonos-v0.1-transformer).\n\n## Features\n\n- FastAPI-based REST API for Zonos Text-to-Speech model\n- Support for both Transformer and Hybrid model variants\n- Docker and docker-compose support with NVIDIA GPU acceleration\n- Production-ready with Gunicorn workers and optimizations\n- Prometheus and Grafana monitoring integration\n- Health checks and comprehensive logging\n- CORS support and Swagger documentation\n- Voice cloning and audio continuation support\n- Fine-grained emotion and audio quality control\n\n## Quick Start\n\n### Using Pre-built Image\n\nThe fastest way to get started is using our pre-built Docker image:\n```bash\ndocker pull ghcr.io/manascb1344/zonos-api-gpu:v1.0.0\ndocker run -d \\\n  --name zonos-api-gpu \\\n  --gpus all \\\n  -p 8000:8000 \\\n  -e CUDA_VISIBLE_DEVICES=0 \\\n  zonos-api-gpu\n```\n\n### Manual Installation\n\n1. Clone the repository with submodules:\n```bash\ngit clone --recursive https://github.com/manascb1344/zonos-api\ncd zonos-api\n```\n\nThe API will be available at `http://localhost:8000`\n\n## Running with Docker\n\n1. Build the container:\n```bash\ndocker build -t zonos-api .\n```\n\n2. Run the container:\n```bash\ndocker run -d \\\n  --name zonos-api \\\n  --gpus all \\\n  -p 8000:8000 \\\n  -e CUDA_VISIBLE_DEVICES=0 \\\n  zonos-api\n```\n\n## Environment Variables\n\n- `CUDA_VISIBLE_DEVICES`: Specify which GPU(s) to use (default: 0)\n- `USE_GPU`: Enable/disable GPU usage (default: true)\n\n## Requirements\n\n- Docker with NVIDIA Container Toolkit installed\n- NVIDIA GPU with CUDA support\n- At least 8GB of GPU memory recommended\n\n## Verifying the Installation\n\nCheck if the API is running:\n```bash\ncurl http://localhost:8000/health\n```\n\n## API Endpoints\n\n### GET /\nRoot endpoint that returns basic API information\n\n### GET /models\nReturns a list of available TTS models\n\n### GET /languages\nReturns a list of supported languages\n\n### GET /model/{model_name}/conditioners\nReturns available conditioners for a specific model\n\n### POST /synthesize\nGenerate speech from text. Example request:\n\n```json\n{\n  \"model_choice\": \"Zyphra/Zonos-v0.1-transformer\",\n  \"text\": \"Hello, this is a test.\",\n  \"language\": \"en-us\",\n  \"emotion_values\": [1.0, 0.05, 0.05, 0.05, 0.05, 0.05, 0.1, 0.2],\n  \"vq_score\": 0.78,\n  \"cfg_scale\": 2.0,\n  \"min_p\": 0.15\n}\n```\n\n## Environment Variables\n\n- `USE_GPU`: Set to \"true\" to enable GPU acceleration (default: true)\n- `PYTHONPATH`: Set to the application root directory\n\n## GPU Support\n\nThe API uses NVIDIA GPU acceleration by default. Make sure you have:\n1. NVIDIA GPU with CUDA support\n2. NVIDIA drivers installed\n3. NVIDIA Container Toolkit installed and configured\n\n## Development\n\n### Prerequisites\n- Python 3.10+\n- NVIDIA GPU with CUDA support (recommended)\n- Docker and docker-compose (for containerized deployment)\n\n### Local Development\n```bash\n# Start in development mode\nuvicorn app.main:app --host 0.0.0.0 --port 8000 --reload\n\n# Or with docker-compose\ndocker-compose up --build\n```\n\n## License\n\nThis project is licensed under the Apache License 2.0 - see the LICENSE file for details. ","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanascb1344%2Fzonos-api","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmanascb1344%2Fzonos-api","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanascb1344%2Fzonos-api/lists"}