Audio Transcription & Live Interpreter

Tracking since Apr 1, 2026.

Changelog

• May 18, 2026
  description

  Audio Transcription is a powerful extension that turns your browser into a real-time interpreter. It captures any audio playing in a tab, transcribes it, translates it live, and can even read the results back to you. It works with any audio or video stream, completely independent of whether the source has pre-existing subtitles.
  
  ⚠️ IMPORTANT: This extension requires a local server running on your computer (based on WhisperLive) to process the audio, ensuring your data remains private and operates with low latency.
  
  ✨ Key Features:
  
  • 🗣️ Real-Time Speech-to-Speech: Listen to live translations as they happen. The extension can read the transcribed or translated text aloud, creating a seamless audio interpreting experience.
  • 📝 Live Transcription: Fast and accurate transcription using your local machine's processing power with OpenAI's Whisper AI.
  • 🌐 Instant Translation: Translate live transcriptions on the fly using Google Translate (free) or Google Gemini API for advanced, context-aware translations.
  • 🖼️ Flexible UI Modes: View transcripts in a floating overlay or a dedicated Standalone popup window (perfect for web podcasts, Zoom, Google Meet, or Teams).
  • 📋 Text History: Saves all processed text in a continuous history for easy clipboard copying.
  • 🛡️ Total Privacy: All audio is processed on your local server. No data is sent to third-party cloud transcription services.
  
  
  ⚙️ SERVER INSTRUCTIONS & SOURCE CODE:
  
  To use this extension, you must run the local server. Get the server script and detailed instructions at:
  
  https://github.com/antor44/Audio-Transcription
  
  ⚖️ 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 2.8.6:
  • ⚖️ Licensing Updates: Added comprehensive GPL-3.0 and MIT licensing notices directly into the extension's UI to comply with open-source standards.
  • 🖼️ Visual Updates: Added new and improved screenshots to the store listing.
  • ⚙️ Backend Tweaks: Minor optimizations and updates to the external local server scripts.

  Audio Transcription is a powerful extension that turns your browser into a real-time interpreter. It captures any audio playing in a tab (transcribing it via Whisper AI) or reads existing video subtitles, translates them live, and reads the results back to you via Text-to-Speech (TTS).
  
  🌟 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, this extension acts as a true Live Interpreter for any media stream.
  
  
  ✨ Key Features:
  
  • 🎬 Subtitle TTS Mode: Read aloud and translate existing subtitles from YouTube, Twitch, or any HTML5 video without needing a local 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.
  • 📝 Live Audio Transcription: Fast and accurate transcription from scratch using your local machine's processing power with OpenAI's Whisper AI (WhisperLive server required).
  • 🤖 Instant Translation: Translate live text using Google Translate (free) or the latest Google Gemini (Flash-Lite) & Gemma 4 AI models.
  • 🖼️ 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 completely out-of-the-box. However, to use the advanced "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
  
  
  ⚖️ 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 3.1.0:
  • 🎤 Smart TTS: The voice engine now intelligently waits for sentence boundaries (periods), creating a much more natural and less choppy listening experience.
  • ⭐ Language Selector: Added an optional 'Source Language' menu in Subtitle TTS mode to fix auto-detection edge cases.
  • 🤖 AI Update: Cleaned up deprecated models and added support for the new Gemma 4 generation.
  • 🐞 Bug Fixes: Fixed initial auto-detect hangs, stopped short phrases from being skipped, and fixed the "Stop" button state when tabs are closed.

• May 18, 2026
  short_description

  Real-time transcription, live translation, and speech-to-speech playback for any audio playing in your browser.

  Real-time transcription, live translation, and speech-to-speech playback for browser audio. Includes Subtitle TTS for videos.

• Apr 17, 2026
  description

  Audio Transcription is a powerful extension that turns your browser into a real-time interpreter. It captures any audio playing in a tab, transcribes it, translates it live, and can even read the results back to you. It works with any audio or video stream, completely independent of whether the source has pre-existing subtitles.
  
  ⚠️ IMPORTANT: This extension requires a local server running on your computer (based on WhisperLive) to process the audio, ensuring your data remains private and operates with low latency.
  
  ✨ Key Features:
  
  • 🗣️ Real-Time Speech-to-Speech: Listen to live translations as they happen. The extension can read the transcribed or translated text aloud, creating a seamless audio interpreting experience.
  • 📝 Live Transcription: Fast and accurate transcription using your local machine's processing power with OpenAI's Whisper AI.
  • 🌐 Instant Translation: Translate live transcriptions on the fly using Google Translate (free) or Google Gemini API for advanced, context-aware translations.
  • 🖼️ Flexible UI Modes: View transcripts in a floating overlay or a dedicated Standalone popup window (perfect for web podcasts, Zoom, Google Meet, or Teams).
  • 📋 Text History: Saves all processed text in a continuous history for easy clipboard copying.
  • 🛡️ Total Privacy: All audio is processed on your local server. No data is sent to third-party cloud transcription services.
  
  
  ⚙️ SERVER INSTRUCTIONS & SOURCE CODE:
  
  To use this extension, you must run the local server. Get the server script and detailed instructions at:
  
  https://github.com/antor44/Audio-Transcription
  
  ⚖️ 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 2.8.5:
  
  • Improved transcription/translation for complex languages (Chinese, Japanese, Korean, Arabic).
  • Upgraded core audio engine to the modern AudioWorklet API for better performance.
  • Translation is more reliable: fixed truncation bugs and improved Gemini API error handling.
  • Fixed a bug where a "ghost" overlay could remain visible on new tabs.
  • UI updates: Translation errors are now clearly visible in the status bar.

  Audio Transcription is a powerful extension that turns your browser into a real-time interpreter. It captures any audio playing in a tab, transcribes it, translates it live, and can even read the results back to you. It works with any audio or video stream, completely independent of whether the source has pre-existing subtitles.
  
  ⚠️ IMPORTANT: This extension requires a local server running on your computer (based on WhisperLive) to process the audio, ensuring your data remains private and operates with low latency.
  
  ✨ Key Features:
  
  • 🗣️ Real-Time Speech-to-Speech: Listen to live translations as they happen. The extension can read the transcribed or translated text aloud, creating a seamless audio interpreting experience.
  • 📝 Live Transcription: Fast and accurate transcription using your local machine's processing power with OpenAI's Whisper AI.
  • 🌐 Instant Translation: Translate live transcriptions on the fly using Google Translate (free) or Google Gemini API for advanced, context-aware translations.
  • 🖼️ Flexible UI Modes: View transcripts in a floating overlay or a dedicated Standalone popup window (perfect for web podcasts, Zoom, Google Meet, or Teams).
  • 📋 Text History: Saves all processed text in a continuous history for easy clipboard copying.
  • 🛡️ Total Privacy: All audio is processed on your local server. No data is sent to third-party cloud transcription services.
  
  
  ⚙️ SERVER INSTRUCTIONS & SOURCE CODE:
  
  To use this extension, you must run the local server. Get the server script and detailed instructions at:
  
  https://github.com/antor44/Audio-Transcription
  
  ⚖️ 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 2.8.6:
  • ⚖️ Licensing Updates: Added comprehensive GPL-3.0 and MIT licensing notices directly into the extension's UI to comply with open-source standards.
  • 🖼️ Visual Updates: Added new and improved screenshots to the store listing.
  • ⚙️ Backend Tweaks: Minor optimizations and updates to the external local server scripts.

Permissions & access

Permissions

storageactiveTabtabstabCapturescriptingtts

Host access

https://generativelanguage.googleapis.com/*, https://clients5.google.com/*

Screenshots