Kevin Lin releases open-source Violin video translation pipeline
Kevin Lin introduced Violin, an open-source video translation pipeline that combines multilingual automatic speech recognition, large language model translation, and text-to-speech synthesis. The system extracts audio, transcribes speakers, translates segments, and generates dubbed audio with synchronized subtitles while supporting voice personalization and a video-grounded chat interface. It runs as a web app at www.violin-ai.com, via command line, and as an agent skill under an MIT license, with its repository hosted on Together AI and development supported by Stanford associate professor James Zou.
#263Andrew Carr 🤸@ANDREW_N_CARRclaude design in the wild
Kevin Lin@KevinQHLin🌟Introducing🎻Violin — an Open-source Video Translation Skill. 📹Video is the dominant medium on the internet, yet most high-quality content (lecture, talk, podcast) is locked behind a single language, leaving global audiences behind. So we built Violin: a video skill that combines speech recognition, LLM translation, and speech synthesis into one seamless pipeline. 🌐 Demo: https://www.violin-ai.com 📝 Blog: https://www.together.ai/blog/violin-open-source-translation-skill 🔗 GitHub: https://github.com/shang-zhu/violin ✨Key Features: 🎙️High-quality multilingual ASR & Translation & TTS. 🗣️Personalize translation & voice (turn an academic talk into something children can follow). 💬Chat with the video — ask any questions grounded in the video. 🧩Support Web app, CLI, and Agent skill 🍃Fully open-source under MIT. ❤️Built with the wonderful @ShangZhu18 and advised by @james_y_zou ! All features powered by @togethercompute . Try it and let us know what you think! 🎻
#690James Zou@JAMES_Y_ZOUCheck out Violin🎻— great open source framework to translate educational videos into different languages. Handles long videos efficiently.
Violin also enables you to chat and ask questions about the video in real time!
Great job by @ShangZhu18 and @KevinQHLin!
Kevin Lin@KevinQHLin🌟Introducing🎻Violin — an Open-source Video Translation Skill. 📹Video is the dominant medium on the internet, yet most high-quality content (lecture, talk, podcast) is locked behind a single language, leaving global audiences behind. So we built Violin: a video skill that combines speech recognition, LLM translation, and speech synthesis into one seamless pipeline. 🌐 Demo: https://www.violin-ai.com 📝 Blog: https://www.together.ai/blog/violin-open-source-translation-skill 🔗 GitHub: https://github.com/shang-zhu/violin ✨Key Features: 🎙️High-quality multilingual ASR & Translation & TTS. 🗣️Personalize translation & voice (turn an academic talk into something children can follow). 💬Chat with the video — ask any questions grounded in the video. 🧩Support Web app, CLI, and Agent skill 🍃Fully open-source under MIT. ❤️Built with the wonderful @ShangZhu18 and advised by @james_y_zou ! All features powered by @togethercompute . Try it and let us know what you think! 🎻