jamesob
Featured
local-llm
A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It uniquely captures internal tab audio instead of microphone input, ensuring clear transcription even from noisy environments, and offers a dynamic AI summarizer supporting a wide range of providers including local Ollama.
Who it is for
- Students and professionals attending online lectures or meetings
- Content creators needing transcripts of web audio/video
- Privacy-conscious users who want local, no-telemetry tools
- Developers exploring speech-to-text and AI summarization integrations
Use cases
- Transcribing YouTube videos, podcasts, or webinars in real time
- Generating concise summaries of long conference calls or presentations
- Searching and extracting specific phrases from recorded web audio
- Exporting transcripts for note-taking or documentation
Strengths
- Captures tab audio directly, avoiding background noise and improving accuracy
- Real-time streaming transcription with OpenAI Whisper, supporting multiple languages
- Supports a wide range of AI providers for summarization (OpenAI, Anthropic, Google, Groq, local Ollama, etc.)
- 100% local storage with no telemetry, ensuring user privacy
Considerations
- Requires a valid OpenAI API key for core transcription functionality
- Only works on Chromium-based browsers (Chrome, Edge, Brave)
- AI summarization incurrs additional API costs depending on provider chosen
README quick start
🎙️ Live Tab Transcriber
Live Tab Transcriber is a powerful, privacy-focused Chrome Extension that captures audio directly from your active browser tab and converts it into accurate, real-time text. Unlike standard speech-to-text tools that rely on your microphone, this extension captures the tab's internal audio, ensuring crystal-clear transcription without background noise.
It also features a Dynamic AI Summarizer, allowing you to instantly generate concise summaries using OpenAI, Anthropic (Claude), Google (Gemini), Groq, or even your local Ollama instance.
✨ Key Features
Core Transcription
- Tab Audio Capture: Records audio directly from the browser tab (YouTube, Udemy, Zoom, Spotify, etc.) instead of the microphone.
- Real-Time Processing: Streams audio in optimized WAV chunks for near-instant transcription via OpenAI Whisper.
- High Accuracy: Leverages OpenAI's industry-leading Whisper API for precise speech-to-text, even with accents or background music.
- Multi-Language Support: Transcribe in English, Hindi, Spanish, French, German, Japanese, and more.
🤖 Dynamic AI Summarization
- Universal AI Router: Don't just stick to OpenAI! Choose your favorite LLM for summarization.
- Supported Providers: OpenAI (GPT-4o-mini), Anthropic (Claude), Google (Gemini), Groq, DeepSeek, Mistral, Together AI, and local Ollama.
- Concise Feedback: Generates a punchy, 1-2 sentence "TL;DR" summary of your transcript instantly.
🛠️ Productivity Tools
- Live Side Panel: Watch the transcript build in real-time without leaving your current tab.
- Smart Search: Instantly highlight and find specific words or phrases within the transcript.
- Export & Copy: Copy text to your clipboard or export the full transcript as a
.txtfile. - Local History: Automatically saves sessions locally. Access your past transcripts even after restarting the browser.
🔒 Privacy & Performance
- 100% Local Storage: Transcript history and settings are stored in
chrome.storage.local. No external databases. - No Telemetry: Zero tracking, zero analytics.
- Optimized Audio Engine: Uses
AudioWorkletand raw WAV encoding to prevent browser memory leaks and API format errors.
Prerequisites
Before using the extension, you will need:
- Google Chrome (or any Chromium-based browser like Edge/Brav
Description
An AI Powered Google Extention which scraps data from voice from the system and also summarise the content
Related repositories
Similar projects matched by category, topics, and programming language.
MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.