{"id":21046006,"url":"https://github.com/axshatind/xethscribe","last_synced_at":"2025-12-31T00:24:49.122Z","repository":{"id":255832972,"uuid":"853706888","full_name":"axshatInd/XethScribe","owner":"axshatInd","description":"XethScribe is an AI-driven web application designed for real-time audio transcription and translation, leveraging advanced models like OpenAI Whisper for speech recognition. It seamlessly processes audio inputs to deliver accurate, timestamped text outputs for various use cases.","archived":false,"fork":false,"pushed_at":"2024-09-07T13:43:34.000Z","size":63,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-20T17:49:14.683Z","etag":null,"topics":["css","html","javascript","machine-learning","openai-whisper","react","transcription","translation","vite","web-workers","xenova-transformers"],"latest_commit_sha":null,"homepage":"https://xethscribe.vercel.app","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/axshatInd.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}},"created_at":"2024-09-07T09:58:57.000Z","updated_at":"2024-09-07T13:47:42.000Z","dependencies_parsed_at":"2024-09-07T11:21:53.178Z","dependency_job_id":"43e20b9b-75b5-430d-999d-31589834e8b5","html_url":"https://github.com/axshatInd/XethScribe","commit_stats":null,"previous_names":["axshatind/xethscribe"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/axshatInd%2FXethScribe","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/axshatInd%2FXethScribe/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/axshatInd%2FXethScribe/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/axshatInd%2FXethScribe/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/axshatInd","download_url":"https://codeload.github.com/axshatInd/XethScribe/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243489826,"owners_count":20299010,"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":["css","html","javascript","machine-learning","openai-whisper","react","transcription","translation","vite","web-workers","xenova-transformers"],"created_at":"2024-11-19T14:27:40.047Z","updated_at":"2025-12-31T00:24:49.111Z","avatar_url":"https://github.com/axshatInd.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# XethScribe\n\nXethScribe is a lightweight, AI-driven web application that offers real-time audio transcription and translation. It utilizes state-of-the-art models like OpenAI's Whisper for speech recognition and Xenova's NLLB-200 for translations, providing accurate and timestamped text outputs. This tool is ideal for transcribing conversations, speeches, or meetings and translating them efficiently.\n\n## Features\n\n- **Real-time Transcription**: Converts speech to text instantly with accurate timestamps.\n- **Automatic Translation**: Supports multilingual translations using advanced AI models.\n- **Lightweight Interface**: User-friendly interface for seamless file uploads and transcription playback.\n- **On-the-fly Processing**: Handles audio streams and files with fast processing times.\n- **Modular Design**: Easily customizable and extendable for additional features or integrations.\n\n## Technologies Used\n\n- **React**: For building the front-end user interface.\n- **Tailwind CSS**: For responsive and modern styling.\n- **Vite**: For fast bundling and development experience.\n- **OpenAI Whisper**: For automatic speech recognition (ASR) in English.\n- **Xenova NLLB-200**: For accurate and scalable translations between languages.\n- **Web Workers**: For running AI models and transcription tasks in the background without blocking the UI.\n\n## Getting Started\n\n### Prerequisites\n\n- **Node.js** (v16 or higher)\n- **npm** (v7 or higher)\n\n### Installation\n\n1. Clone the repository:\n\n   ```bash\n   git clone https://github.com/axshatInd/XethScribe.git\n   cd XethScribe\n   ```\n\n2. Install dependencies:\n\n   ```bash\n   npm install\n   ```\n\n3. Start the development server:\n\n   ```bash\n   npm run dev\n   ```\n\n4. Open [http://localhost:3000](http://localhost:3000) to view it in the browser.\n\n### Build for Production\n\n```bash\nnpm run build\n```\n\n## Usage\n\n1. Upload an audio file or use a live audio stream.\n2. The app will automatically transcribe the audio and display the results in real-time.\n3. For translation, the output can be selected in different languages using the available options.\n\n---\n\nFeel free to contribute or submit any issues!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faxshatind%2Fxethscribe","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faxshatind%2Fxethscribe","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faxshatind%2Fxethscribe/lists"}