{"id":30701060,"url":"https://github.com/gyyyn/openwebtts","last_synced_at":"2025-09-02T13:03:31.115Z","repository":{"id":310915037,"uuid":"1041618887","full_name":"Gyyyn/OpenWebTTS","owner":"Gyyyn","description":"Open source Speechify alternative. Read PDFs and EPUBs with local models.","archived":false,"fork":false,"pushed_at":"2025-08-28T15:08:10.000Z","size":228,"stargazers_count":13,"open_issues_count":7,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-08-28T22:23:56.978Z","etag":null,"topics":["ai","coqui-ai","coqui-tts","kokoro-82m","kokoro-tts","piper-tts","python","pytorch","stt","tts","webapp","whisper"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Gyyyn.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"zenodo":null}},"created_at":"2025-08-20T18:55:32.000Z","updated_at":"2025-08-28T19:33:20.000Z","dependencies_parsed_at":"2025-08-21T02:30:37.458Z","dependency_job_id":"8d191a13-60d8-4b97-9830-9d9047356419","html_url":"https://github.com/Gyyyn/OpenWebTTS","commit_stats":null,"previous_names":["gyyyn/openwebtts"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Gyyyn/OpenWebTTS","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gyyyn%2FOpenWebTTS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gyyyn%2FOpenWebTTS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gyyyn%2FOpenWebTTS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gyyyn%2FOpenWebTTS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Gyyyn","download_url":"https://codeload.github.com/Gyyyn/OpenWebTTS/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gyyyn%2FOpenWebTTS/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273287682,"owners_count":25078575,"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","status":"online","status_checked_at":"2025-09-02T02:00:09.530Z","response_time":77,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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","coqui-ai","coqui-tts","kokoro-82m","kokoro-tts","piper-tts","python","pytorch","stt","tts","webapp","whisper"],"created_at":"2025-09-02T13:01:54.480Z","updated_at":"2025-09-02T13:03:31.064Z","avatar_url":"https://github.com/Gyyyn.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# OpenWebTTS: Local Text-to-Speech Web UI\n\nOpenWebTTS is a local web-based application that provides a simple interface for generating speech using multiple Text-to-Speech (TTS)  or Speech-to-Text (STT) engines.\n\n\u003cimg width=\"2278\" height=\"1525\" alt=\"image\" src=\"https://github.com/user-attachments/assets/869f16f5-1a51-4368-9720-7e7ba8e623da\" /\u003e\n\n\n## Features\n\n- **Simple Web Interface**: A clean UI for text input and audio generation.\n- **Multiple Engine Support**: Use Piper, Kokoro or Coqui for TTS or OpenAI Whisper for STT.\n- **Real-time Generation**: Generates as you listen for smooth playback or recording.\n\n## Project Structure\n\n```\nOpenWebTTS/\n|\n├── app.py                 # Main FastAPI application\n├── requirements.txt       # Python dependencies\n├── README.md              # This file\n├── .gitignore             # Git ignore file\n├── flatpak-manifest.yml   # Flatpak manifest for Linux\n|\n├── functions/\n|   ├── users.py           # User management and authentication\n│   ├── gemini.py          # Gemini API\n│   ├── piper.py           # Piper TTS\n│   ├── whisper.py         # OpenAI's Whisper STT\n|   ├── kitten.py          # Kitten TTS\n│   └── kokoro.py          # Kokoro functions\n|\n├── models/                # Place your TTS models here\n|   ├── coqui/\n|   ├── piper/\n|   └── kokoro/\n|\n├── translations/          # Translations\n|   └── en/ (etc...)\n|\n├── users/\n│   └── *.json             # User settings and preferences\n|\n├── static/\n|   ├── css/               # Stylesheets\n|   ├── js/                # JavaScript files  \n|   ├── audio/             # Static audio  \n|   └── audio_cache/       # Generated audio cache\n|\n└── templates/\n    ├── config.html        # Configuration page\n    └── index.html         # Main HTML page\n```\n\n## Setup and Installation\n\n### 1. Prerequisites\n\n- Python 3.11 (Recommended). **Note:** Other Python versions might not be fully compatiible due to dependencies. If you wish to use 3.12 or above, make sure to adjust the `requirements.txt` file accordingly, and note that not all functions will work.\n- `pip` and `venv` for managing dependencies.\n- `espeak-ng` for Kokoro.\n\n### 2. Create a Virtual Environment\n\nIt is highly recommended to use a virtual environment to avoid conflicts with system-wide packages. **Note:** Make sure you're using the correct python version (3.11 recommended) to create the venv.\n\n```bash\n# Navigate to the project directory\ncd /path/to/OpenWebTTS\n\n# Create a virtual environment\npython3.11 -m venv venv\n\n# Activate the virtual environment\n# On macOS and Linux:\nsource venv/bin/activate\n# On Windows:\n.\\venv\\Scripts\\activate\n```\n\n### 3. Install Dependencies\n\nInstall all the required Python libraries using the `requirements.txt` file. **Note:** If you have an older graphics card PyTorch might need to be installed differently. Check the PyTorch docs.\n\n```bash\npip install -r requirements.txt\npip install https://github.com/KittenML/KittenTTS/releases/download/0.1/kittentts-0.1.0-py3-none-any.whl\n```\n\n### 4. Download and Place TTS Models\n\n#### Piper\n\n1.  Use the integrated model downloader (recommended)\n\nOr\n\n1.  Download a Piper voice model from the [official repository](https://huggingface.co/rhasspy/piper-voices/tree/main).\n2.  Place the files inside `models/piper/`. For example: `models/piper/en_US-lessac-medium.onnx` and `models/piper/en_US-lessac-medium.onnx.json`.\n\n#### Kokoro\n\n1.  Use the integrated model downloader (recommended)\n\nOr\n\n1.  Download a model from the [officla repository](https://huggingface.co/hexgrad/Kokoro-82M/tree/main/voices).\n2.  Place the file inside `models/kokoro/`. For example: `models/kokoro/af_heart.pt`\n\n#### Coqui TTS (In development.)\n\n1.  Find a model from the [Coqui TTS releases](https://github.com/coqui-ai/TTS/releases) or train your own.\n2.  A Coqui model is typically a directory containing files like `model.pth`, `config.json`, and `speakers.json` (for multi-speaker models).\n3.  Place the entire model directory inside `models/coqui/`. For example: `models/coqui/your-coqui-model/`.\n\n## How to Run the Application\n\nOnce you have installed the dependencies and placed your models, you can start the web server.\n\n```bash\npython app.py\n```\n\nThe application will be available at `http://127.0.0.1:8000`. If you want the app to be available to your LAN, pass the `--host=0.0.0.0` flag.\n\n### Desktop Mode (Experimental)\n\nYou can also run OpenWebTTS as a desktop app using a lightweight webview window. This requires a webview backend such as `webkit2gtk`. This is still experimental, so if you experience any issues try running it as a web app instead.\n\n```bash\npython app.py --desktop\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgyyyn%2Fopenwebtts","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgyyyn%2Fopenwebtts","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgyyyn%2Fopenwebtts/lists"}