Huanshere /VideoLingo
Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音,一键全自动视频搬运AI字幕组
★ 19,269⑂ 2,127👁 105⑃ 179● 458▤ 50
+18
Daily
19,269
stars
2,127
forks
105
watchers
179
prs
458
issues
50
releases
README
Connect the World, Frame by Frame English|简体中文|繁體中文|日本語|Español|Русский|Français 🌟 Overview (Try VL Now!) VideoLingo combines speech recognition, subtitle translation, segmentation and dubbing in a Streamlit interface. It produces subtitle files and optionally subtitled or dubbed videos. Translation quality depends on the source audio, language and chosen models. Key features: - 🎥 YouTube video download via yt-dlp - Word-level speech recognition and alignment with Qwen3-ASR + Qwen3-ForcedAligner - 📝 NLP and AI-powered subtitle segmentation - 📚 Custom + AI-generated terminology for coherent translation - Direct translation with optional reflection and natural rewriting - Subtitle segmentation with configurable length limits - 🗣️ Dubbing with GPT-SoVITS, OpenAI, Edge TTS, and more - 🚀 One-click startup and processing in Streamlit - 🌍 Multi-language support in Streamlit UI - 📝 Detailed logging with progress resumption - 🔍 Model searchbox with API auto-fetch — search and filter from your provider's full model list - ⏯️ Task control — pause, resume, or stop processing at any step The workflow combines transcription, translation, subtitle layout and dubbing in one project. 🎥 Demo Dual Subtitles --- https://github.com/user-attachments/assets/a5c3d8d1-2b29-4ba9-b0d0-25896829d951 Cosy2 Voice Clone --- https://github.com/user-attachments/assets/e065fe4c-3694-477f-b4d6-316917df7c0a GPT-SoVITS with my voice --- https://github.com/user-attachments/assets/47d965b2-b4ab-4a0b-9d08-b49a7bf3508c Language Support Input languages: 🇺🇸 English 🤩 | 🇷🇺 Russian 😊 | 🇫🇷 French 🤩 | 🇩🇪 German 🤩 | 🇮🇹 Italian 🤩 | 🇪🇸 Spanish 🤩 | 🇯🇵 Japanese 😊 | 🇨🇳 Chinese 🤩 Dubbing languages depend on the selected TTS method. Installation VideoLingo supports Windows, macOS (Apple Silicon / Intel), and Linux. Ask your local AI agent 🤖 If you use an AI agent that can operate your computer, send it this prompt: Install and launch GitHub's Huanshere/VideoLingo on my computer. Windows: one-click install 🎉 1. Download Source code (zip) from the latest Release, extract it to your Desktop or another folder, and open the folder. 2. Double-click OneKeyStart.bat and keep the window open. On the first run, it automatically installs uv, Python 3.12, the app dependencies, and FFmpeg. An internet connection is required. 3. After installation, VideoLingo opens automatically in your browser. Enter your API URL, key, and model in the sidebar to start using it. Install from source (Windows, macOS, Linux) bash git clone https://github.com/Huanshere/VideoLingo.git && cd VideoLingo uv run start.py To start it later, run uv run start.py again from the VideoLingo folder. Apple Silicon uses MLX; Intel Macs use CPU recognition. By default, Intel Mac dubbing uses the new voice without the original background sound. Docker (optional) For a Linux NVIDIA container deployment, install Docker, a compatible GPU driver and the NVIDIA Container Toolkit. The image
Top issues
#441这个项目的一些局限性4 comments · 2025-04-25#375苹果芯片使用videotoolbox硬件加速FFmpeg视频合成4 comments · 2025-01-24#330功能需求:希望能加入源字幕做校对的步骤2 comments · 2024-12-07#314gpt 的 prompt 不合适2 comments · 2024-12-03#634处理字幕的时候速度比V2版慢很多1 comments · 2026-10-14#547可否加入火山引擎的tts1 comments · 2026-04-09#533这个新版v3.0.1的配音效果是不是不如以前了?1 comments · 2026-03-12#524大佬能原生自持indexTTS2.0吗?1 comments · 2026-01-16
Latest release
VideoLingo v3.2.0 🎨 v3.2.0 2026-11-13VideoLingo v3.2.0 🎨 Subtitles that look right in every language, an optional PyTorch-free engine for local Qwen3-ASR, and an installer that leaves your global pip settings alone. 🚀 What's new - Built-in multilingual subtitle typesetting. Burned-in subtitles no longer use one system font for everything. Each of 33 languages has its own font, size and spacing, whether it is the translated row or the source row. Lines are broken by their rendered width, measured with HarfBuzz, preferably at punctuation and between words; Chinese, Japanese and Thai are split into words with BudouX. Arabic, Dev