Audio Transcription & Live Interpreter

Audio Transcription is a powerful extension that turns your browser into a real-time interpreter. It offers two distinct ways to process speech: reading existing video subtitles for instant convenience, or transcribing live audio from scratch via Whisper AI as the ultimate fallback for any media stream. 🌟 Designed with privacy and efficiency in mind, it is optimized to run smoothly on low-resource computers and operates as independently from cloud services as possible. Compatible with Linux, Windows, and macOS. ✨ Key Features: • 🎬 Subtitle TTS Mode (Most Convenient): The fastest and easiest option. It reads aloud and translates existing subtitles from supported HTML5 video players directly in your browser. It requires the video to have a supported subtitle track, but it works completely out-of-the-box with no local server required. • 📝 Live Audio Transcription (The Ultimate Solution): The definitive fallback for absolutely any scenario. When a video has no subtitles—or Subtitle TTS cannot capture them—this mode transcribes the raw audio from scratch using your local machine's processing power and OpenAI's Whisper AI (Requires running a local WhisperLive server). • 🌐 Source Language Control: Rely on smart auto-detection, or manually select the subtitle language for maximum accuracy. • 🗣️ Real-Time Speech-to-Speech: Listen to live translations with a natural, fluid voice that buffers complete sentences for a seamless experience. • 🤖 Instant Translation: Translate live text using Google Translate (free) or the best Gemini and Gemma models for translation via a free or very cheap Google Gemini API key. • 🖼️ Flexible UI Modes: View transcripts in a floating overlay or a dedicated Standalone popup window. • 🛡️ Total Privacy: Local audio processing and transparent open-source code. ⚙️ SERVER INSTRUCTIONS & SOURCE CODE: The "Subtitle TTS" mode works immediately after installation. However, to use the universal "Live Audio Transcription" feature, you must run the local WhisperLive server on your computer. Get the server scripts and detailed setup instructions at: https://github.com/antor44/Audio-Transcription 📥 Download & Installation • Extension: For automatic updates, install from the Official Chrome Web Store: https://chromewebstore.google.com/detail/audio-transcription-live/mgekiekmhamibkobnlfbphhifjkhkohh (This is all you need for Subtitle TTS mode). • Local Backend Server: For WhisperLive audio capture mode, download the latest "Audio-Transcription-v3.x.x.zip" from our GitHub repository and unzip it. Install the library (preferably in a Python virtual environment) via your terminal using: pip install whisper-live Then, run your local server using the WhisperLive_server.sh and run_server.py files you will find inside the zip file (in reality, these are the only two files you need for the server). 🌐 Compatibility Notes & Technical Limitations This extension is designed with an ambitious goal: to provide a universal, real-time interpretation experience across major video platforms, live news networks, on-demand media, and custom HTML5 players, whether using native captions or live AI transcription. This flexibility comes with inherent technical challenges: • Complex Languages: Spaceless CJK scripts and right-to-left languages (like Arabic and Hebrew) require specialized text processing. • Auto-Generated Captions: Subtitles generated by AI rather than manually edited often lack punctuation, have unusual line breaks, or roll continuously on the screen, making real-time sentence detection difficult. • Real-Time Processing: The extension does not pre-download full subtitle files (.vtt or .srt). It reads text strictly live as it appears on screen. Because it must wait for enough words to form a logical sentence before translating and speaking, a small amount of latency is normal. As a result, occasional edge cases may occur on specific websites, languages, or custom video players. The extension is continuously refined to improve reliability across these diverse environments. 🛡️ Privacy & Permissions To maintain strict privacy, this extension does not ask for access to all websites when you install it. However, some news sites embed videos from other sources (like external videos inside an article). To read subtitles from these cross-origin iframes, Chrome will safely prompt you to grant permission for that specific player only when you click "Start". No user tracking or credentials are ever sent. ⚖️ LICENSE: This is a free and open-source project distributed under the GNU General Public License v3.0 (GPL-3.0). For more details, visit the GitHub repository. --- 🆕 WHAT'S NEW IN VERSION 3.6.6: • 📱 TikTok & YouTube Shorts Support: Subtitle TTS now fully supports short-form video feeds! • 🔄 Seamless Scrolling: The voice queue survives when you swipe to the next TikTok or Short. Trailing sentences from the previous clip will finish speaking naturally without being cut off by the new video. • 🌐 Deep Subtitle Fetching: On TikTok, the extension dynamically fetches hidden native subtitle files directly from page data, even on Explore pages. • ⚡ Smart Auto-Activation: Automatically detects and activates subtitle toggles on TikTok and YouTube Shorts only when they are turned off.