{"data":{"slug":"royshil-obs-localvocal","name":"obs-localvocal","tagline":"An OBS plugin for local speech recognition and captioning","github_url":"https://github.com/royshil/obs-localvocal","owner":"royshil","repo":"obs-localvocal","owner_avatar_url":"https://avatars.githubusercontent.com/u/441170?v=4","primary_language":"C++","stars":1561,"forks":120,"topics":["ai","live-streaming","livestream","obs","obs-studio","obs-studio-plugin","openai-whisper","plugin","real-time-transcription","realtime-transcribe","realtime-translator","speech-recognition","speech-to-text","transcription","translation","whisper","whisper-cpp"],"archived":false,"github_pushed_at":"2026-05-20T08:09:39+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/royshil-obs-localvocal","markdown_url":"https://www.graphcanon.com/tools/royshil-obs-localvocal.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/royshil-obs-localvocal","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=royshil-obs-localvocal","description":"OBS plugin for local speech recognition and captioning using AI","homepage_url":"https://obsproject.com/forum/resources/localvocal-live-stream-ai-assistant.1769/","license":"GPL-2.0","open_issues":55,"watchers":14,"ai_summary":"OBS plugin that supports real-time transcription and translation using AI.","readme_excerpt":"## Repo sponsors: [Recall.ai](https://www.recall.ai/product/desktop-recording-sdk?utm_source=github&utm_medium=sponsorship&utm_campaign=royshil-obs-localvocal) - API for desktop recording\n\nIf you’re looking for a hosted desktop recording API, consider checking out [Recall.ai](https://www.recall.ai/product/desktop-recording-sdk?utm_source=github&utm_medium=sponsorship&utm_campaign=royshil-obs-localvocal), an API that records Zoom, Google Meet, Microsoft Teams, in-person meetings, and more.\n\n# LocalVocal - Speech AI assistant OBS Plugin\n\n
\n\n\n\n\n\n\n
\n
\n\n## Downloads\n\n### Windows\n\nOS | Generic (x86_64) | NVidia (x86_64) | AMD (x86_64)\n:-:|:-------:|:------:|:---:\nWindows 10/11 | [-0078d6?style=for-the-badge&logo=windows&logoColor=white)](https://github.com/locaal-ai/obs-localvocal/releases/download/0.6.2/obs-localvocal-0.6.2-windows-x64-generic-Installer.exe) | [-0078d6?style=for-the-badge&logo=windows&logoColor=white)](https://github.com/locaal-ai/obs-localvocal/releases/download/0.6.2/obs-localvocal-0.6.2-windows-x64-nvidia-Installer.exe) | [-0078d6?style=for-the-badge&logo=windows&logoColor=white)](https://github.com/locaal-ai/obs-localvocal/releases/download/0.6.2/obs-localvocal-0.6.2-windows-x64-amd-Installer.exe)\n\n### Linux\n\nOS | Generic (x86_64) | NVidia (x86_64) | AMD (x86_64)\n:-:|:-------:|:------:|:---:\nUbuntu 22.04 (Jammy) .deb | [-FCC624?style=for-the-badge&logo=linux&logoColor=black)](https://github.com/locaal-ai/obs-localvocal/releases/download/0.6.2/obs-localvocal-0.6.2-generic-x86_64-linux-gnu.deb) | [-FCC624?style=for-the-badge&logo=linux&logoColor=black)](https://github.com/locaal-ai/obs-localvocal/releases/download/0.6.2/obs-localvocal-0.6.2-nvidia-x86_64-linux-gnu.deb) | [-FCC624?style=for-the-badge&logo=linux&logoColor=black)](https://github.com/locaal-ai/obs-localvocal/releases/download/0.6.2/obs-localvocal-0.6.2-amd-x86_64-linux-gnu.deb)\n\n### MacOS\n\nMacOS | Intel x86_64 | ARM64 (Apple silicon - M1/M2/M3/M4)\n:----:|:-----:|:------------------:\nGeneric* | | \n12 (Monterey) | | \n13 (Ventura) | | \n14 (Sonoma) | | \n15 (Sequoia) | | \n\n*While variants for specific versions of MacOS _may_ work better on that version of MacOS, the Generic variant is likely the best option. See [MacOS Variants](#mac-os-variants) below for more details\n\nCheck out the [latest releases](https://github.com/locaal-ai/obs-localvocal/releases) for downloads and install instructions.\n\n## Introduction\n\nLocalVocal lets you transcribe, locally on your machine, speech into text and simultaneously translate to any language. ✅ No GPU required, ✅ no cloud costs, ✅ no network and ✅ no downtime! Privacy first - all data stays on your machine.\n\nThe plugin runs [OpenAI's Whisper](https://github.com/openai/whisper) to process real-time speech and predict a transcription, utilizing [Whisper.cpp](https://github.com/ggerganov/whisper.cpp) from [ggerganov](https://github.com/ggerganov) to run the model efficiently on CPUs and GPUs. Translation is done with [CTranslate2](https://github.com/OpenNMT/CTranslate2).\n\n## Usage\n\n

\n \n \n  \n \n \n \n  \n \n \n \n
\n https://youtu.be/ns4cP9HFTxQ\n https://youtu.be/4llyfNi9FGs\n https://youtu.be/R04w02qG26o\n

\n\nDo more with LocalVocal:\n- [RealTime Translation](https://youtu.be/4llyfNi9FGs) \n- [Translate Caption any Application](https://you","github_created_at":"2023-08-10T19:05:18+00:00","created_at":"2026-07-11T12:18:56.999905+00:00","updated_at":"2026-07-30T18:00:29.316641+00:00","categories":[{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"live-streaming","name":"live-streaming"},{"slug":"obs-plugin","name":"obs-plugin"},{"slug":"speech-to-text","name":"speech-to-text"},{"slug":"transcription","name":"transcription"}],"trust":{"provenance":{"is_fork":false,"github_id":677110837,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-30T18:00:28.533Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":71,"last_release_at":"2026-04-21T20:06:11Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:19:03.130Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-30T18:00:29.004Z"},"languages":{"value":["c++"],"source":"github.language","observed_at":"2026-07-30T18:00:29.004Z"},"license_spdx":{"value":"GPL-2.0","source":"github.license","observed_at":"2026-07-30T18:00:29.004Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["The software operates on Windows, Linux (Ubuntu 22.04), and MacOS environments.","Support for translation is included using CTranslate2."],"requires_docker":false},"constraints":{"requires_docker":false},"when_to_use":["When you require privacy-first solutions where all processing of audio and data occurs on the local machine without any cloud-based services.","For those working in environments with limited or unreliable internet connections, as it works entirely offline."],"when_not_to_use":["If your workflow demands GPU acceleration for better performance, given obs-localvocal focuses primarily on CPU but offers limited GPU support.","In scenarios where you need to integrate directly with cloud-hosted services or APIs, since this plugin processes everything locally without internet dependency."],"source":"enrich:decision_facts","observed_at":"2026-07-16T23:21:07.487Z"},"constraint_facets":{"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"The software operates on Windows, Linux (Ubuntu 22.04), and MacOS environments.; Support for translation is included using CTranslate2."},{"label":"Adopt for","value":"Obs-localvocal is an OBS plugin enabling real-time speech-to-text transcription and translation using AI models that run locally."},{"label":"License detail","value":"GPL-2.0"}]}}