Windows-focused Gradio web app for dubbing workflows: YouTube download, vocal separation, Whisper subtitles, translation, and TTS with voice cloning.
michael-chow-arch/StreamLingo
Chrome extension plus local Python service that generates real-time English/Chinese translated captions for YouTube livestreams using Ollama.
Open-source alternative to:Google TranslateYouTube auto-captions
- Stars
- 30
- Forks
- 2
- Open issues
- 0
- Last commit
- 5 days ago
What is it?
StreamLingo shows translated captions inside the YouTube player for livestreams that lack subtitles in your language. It captures the tab's audio in the browser, transcribes speech locally with WhisperLiveKit and faster-whisper, and translates the recognized text with an Ollama model running on your machine. The original audio keeps playing.
It supports English to Chinese, Chinese to English, and automatic source-language detection with either Chinese or English output. Translations are shown in order as readable pages, with optional source text and adjustable font size. Capture continues when the popup closes, and you start and stop it yourself.
The default setup sends audio and text only to services on your machine, and it has no hosted translation service or account. The Windows preview is the tested platform and requires an NVIDIA GPU with CUDA 12, cuBLAS and cuDNN 9, plus Python 3.11 to 3.13 and Chrome 116 or newer. Linux and macOS have not been validated.
Key features
- 01Captures livestream audio directly from the browser tab, with no microphone or virtual audio cable.
- 02Supports English to Chinese, Chinese to English, and auto-detected source language.
- 03Uses your own local Ollama model for translation.
- 04Translates stable segments during continuous speech without waiting for the speaker to pause.
- 05Shows translations with optional source text and adjustable font size.
Use cases
- Following an English-language interview or product launch livestream that has no Chinese captions.
- Watching a Chinese livestream with English subtitles for personal understanding.
- Keeping speech content on your own machine when you do not want to use a cloud translation service.
Topics
FAQ
- What is StreamLingo?
- Chrome extension plus local Python service that generates real-time English/Chinese translated captions for YouTube livestreams using Ollama. StreamLingo shows translated captions inside the YouTube player for livestreams that lack subtitles in your language. It captures the tab's audio in the browser, transcribes speech locally with WhisperLiveKit and faster-whisper, and translates the recognized text with an Ollama model running on your machine. The original audio keeps playing.
- Is StreamLingo free to use? What license does it have?
- StreamLingo is open source under the MIT license. Check the license terms before using it in commercial products.
- Is StreamLingo still maintained?
- Actively maintained. The last commit to StreamLingo was on Oct 13, 2026.
- What can I use StreamLingo for?
- Following an English-language interview or product launch livestream that has no Chinese captions. Watching a Chinese livestream with English subtitles for personal understanding. Keeping speech content on your own machine when you do not want to use a cloud translation service.
- Where can I get StreamLingo?
- The source code and installation instructions are on GitHub: https://github.com/michael-chow-arch/StreamLingo
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Desktop app that transcribes and translates audio and video offline on your computer, powered by OpenAI's Whisper.
An open-source browser extension that shows bilingual webpage translations alongside the original text, with selection translation and AI reading help.
Open-source tool that turns a topic or keyword into a finished short video, handling script, voiceover, stock footage, subtitles and background music automatically.
An edge-native MoE serving engine that runs large open-weight models like DeepSeek-V4 and Qwen3.6 on consumer GPUs by splitting work between GPU and CPU memory.
Open-source, local-first AI meeting assistant that records, transcribes in real time, and generates summaries on macOS and Windows.