littlescribe 1.0.3

Real-time audio transcription with AI summarization

AI Little Scribe

Real-time audio transcription tool that captures both system audio and microphone input, with AI-powered summarization using Amazon Bedrock.

Features

• Real-time transcription of system audio + microphone
• Multi-language support
• AI-powered summary generation
• Speaker identification
• Cross-platform support

Prerequisites

• macOS 14.2+ with AudioTee binary
• AWS credentials configured
• Python 3.7+

Installation & Usage

No installation needed! Use with uvx:

# System audio only (default)
uvx littlescribe

# Microphone only
uvx littlescribe --microphone

# Both system audio + microphone
uvx littlescribe --both

# With custom options
uvx littlescribe --language fr-FR --output meeting.txt --summary summary.txt

Setup AudioTee (macOS only)

git clone https://github.com/makeusabrew/audiotee.git
cd audiotee && make && sudo cp audiotee /usr/local/bin/

Parameters

• --language, -l: Input language code (default: en-US)
• --output, -o: Output file (default: transcription_output.txt)
• --summary, -s: Summary output file (optional)
• --microphone, -m: Record microphone instead of system audio
• --both, -b: Record both microphone and system audio

Press Ctrl+C to stop recording and generate summary.

AWS Setup

Configure AWS credentials via AWS CLI or environment variables:

aws configure

Requires access to Amazon Transcribe and Amazon Bedrock services.

Important Notice

This tool uses AWS services (Amazon Transcribe for speech-to-text and Amazon Bedrock Nova Pro for AI summarization) which may incur charges to your AWS account. Please review AWS pricing for these services before use:

• Amazon Transcribe Pricing
• Amazon Bedrock Pricing

You are responsible for any AWS charges incurred while using this tool.