{"id":26923824,"url":"https://github.com/diegodscamara/whisperlive","last_synced_at":"2026-05-09T00:02:11.159Z","repository":{"id":285388990,"uuid":"957964222","full_name":"diegodscamara/whisperlive","owner":"diegodscamara","description":"🎙️ WhisperLive: Real-time audio transcription powered by OpenAI's Whisper model. Convert live speech to text with high accuracy, supporting multiple languages and real-time processing. Perfect for accessibility, content creation, and live captioning.","archived":false,"fork":false,"pushed_at":"2025-03-31T12:31:00.000Z","size":6,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-31T13:50:44.522Z","etag":null,"topics":["ai","blackhole","numpy","python","wave","whisper"],"latest_commit_sha":null,"homepage":"","language":"Python","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/diegodscamara.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"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":"2025-03-31T12:24:35.000Z","updated_at":"2025-03-31T12:36:21.000Z","dependencies_parsed_at":"2025-03-31T13:50:50.731Z","dependency_job_id":"6e864bb1-cf58-433d-baf6-1a4d9239b552","html_url":"https://github.com/diegodscamara/whisperlive","commit_stats":null,"previous_names":["diegodscamara/whisperlive"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diegodscamara%2Fwhisperlive","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diegodscamara%2Fwhisperlive/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diegodscamara%2Fwhisperlive/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diegodscamara%2Fwhisperlive/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/diegodscamara","download_url":"https://codeload.github.com/diegodscamara/whisperlive/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246741185,"owners_count":20826063,"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","blackhole","numpy","python","wave","whisper"],"created_at":"2025-04-02T01:42:48.171Z","updated_at":"2026-05-09T00:02:11.102Z","avatar_url":"https://github.com/diegodscamara.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# WhisperLive 🎙️\n\nReal-time audio transcription powered by OpenAI's Whisper model.\n\n## Features ✨\n\n- Real-time audio capture and transcription\n- Support for multiple languages (auto-detection)\n- Continuous streaming transcription\n- Automatic sentence detection and formatting\n- Save transcriptions to text files\n- Hallucination prevention mechanisms\n- Clean, formatted output with timestamps\n\n## Requirements 📋\n\n- Python 3.8+\n- BlackHole 2ch (or similar virtual audio device)\n- Required Python packages:\n  - sounddevice\n  - numpy\n  - whisper\n  - wave\n\n## Installation 🚀\n\n1. Clone the repository:\n```bash\ngit clone https://github.com/diegodscamara/whisperlive.git\ncd whisperlive\n```\n\n2. Install dependencies:\n```bash\npip install -r requirements.txt\n```\n\n3. Install BlackHole 2ch (macOS):\n```bash\nbrew install blackhole-2ch\n```\n\nFor other operating systems, use an equivalent virtual audio device.\n\n## Models 🤖\n\nWhisperLive uses OpenAI's Whisper models for transcription. The models are automatically downloaded when you first run the application. By default, it uses the \"base\" model, which offers a good balance between accuracy and performance.\n\nThe models are stored in the `models` directory but are not included in the repository due to their size. They will be downloaded automatically when needed.\n\nAvailable models:\n- `tiny` (74MB) - Fastest, least accurate\n- `base` (142MB) - Good balance for most uses\n- `small` (466MB) - More accurate but slower\n- `medium` (1.5GB) - Even more accurate\n- `large` (2.9GB) - Most accurate, slowest\n\nTo change the model, modify the `model_name` parameter in `main.py`:\n```python\ntranscriber = WhisperTranscriber(model_name=\"base\")  # Change \"base\" to your preferred model\n```\n\n## Usage 💡\n\n1. Set up your virtual audio device (BlackHole 2ch) as your system's audio output.\n\n2. Run the transcription:\n```bash\npython main.py\n```\n\n3. Start speaking or playing audio. The transcription will appear in real-time.\n\n4. Press `Ctrl+C` to stop the transcription.\n\n## Output Files 📁\n\nThe app creates two types of files in the `recordings` directory:\n- `recording_YYYYMMDD_HHMMSS.wav` - Audio recording\n- `transcript_YYYYMMDD_HHMMSS.txt` - Text transcription\n\n## Configuration ⚙️\n\nDefault settings in `main.py`:\n- Sample rate: 16000 Hz\n- Buffer size: 5 seconds\n- Minimum process size: 2 seconds\n- Model: \"base\" (can be changed to other Whisper models)\n\n## Contributing 🤝\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n## License 📄\n\nMIT License - feel free to use this project for any purpose.\n\n## Acknowledgments 🙏\n\n- [OpenAI Whisper](https://github.com/openai/whisper) for the amazing speech recognition model\n- [sounddevice](https://python-sounddevice.readthedocs.io/) for audio handling\n- [BlackHole](https://github.com/ExistentialAudio/BlackHole) for virtual audio routing ","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdiegodscamara%2Fwhisperlive","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdiegodscamara%2Fwhisperlive","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdiegodscamara%2Fwhisperlive/lists"}