Skip to main content

Real-time audio transcription with AI summarization

Project description

AI Little Scribe

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

⚠️ IMPORTANT: AudioTee Required

This tool requires AudioTee to be installed on your system to capture system audio. Without AudioTee, the tool will not work.

Install AudioTee First (Required)

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

Features

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

Prerequisites

  • macOS 14.2+
  • AudioTee binary installed (see installation above)
  • 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:

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

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

littlescribe-1.2.0.tar.gz (1.8 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

littlescribe-1.2.0-py3-none-any.whl (8.9 kB view details)

Uploaded Python 3

File details

Details for the file littlescribe-1.2.0.tar.gz.

File metadata

  • Download URL: littlescribe-1.2.0.tar.gz
  • Upload date:
  • Size: 1.8 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.4

File hashes

Hashes for littlescribe-1.2.0.tar.gz
Algorithm Hash digest
SHA256 8c88b083ce8b6beefd76b968ec7b36c6ef9bdc7160a34aad2a1c43216bb4393b
MD5 4e9b830752fe96f5c2b0a8f656674c15
BLAKE2b-256 9db6bcebdb9d60d44ae942a91ceba0e5896f0075bca23f410bc43575b1f6be50

See more details on using hashes here.

File details

Details for the file littlescribe-1.2.0-py3-none-any.whl.

File metadata

File hashes

Hashes for littlescribe-1.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d3323e8a617668f2849b19b192fe6e53b91c39c9cfc448e1c96cc55a5a0e36f8
MD5 9778f869a3ba4668fcb62bbd686719ae
BLAKE2b-256 ff84bcb0cc10d05884ecccd26c84d0e62bda9d3cad87815f4d0871b45663dd49

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page