All work

AI tool, Python

Turns a meeting recording into notes, decisions and action items, then sends them to Slack, Markdown or JSON. A command line and an API.

EchoScribe, edited screenshot
Surfaces
CLI, API, Watcher
Outputs
Slack / MD / JSON
Container
GHCR

The problem

Every meeting has 30 minutes of decisions and 5 hours of context. Good written summaries take humans 20 minutes to compose, and they always wait until morning, after the team has already moved on.

What I built

EchoScribe automates the meeting-to-Slack-digest workflow. Pull audio from a recording source, transcribe via Whisper, run a multi-step summarisation chain (decisions, action items, sentiment, follow-ups), and post a structured digest to Slack, Markdown, or JSON. Ships as a Python CLI, a FastAPI server, and a directory watcher. One OpenAI key powers all three. Docker image on GHCR.

A pipeline that runs the moment the recording ends. Whisper for transcription, a multi-step GPT-4o chain that extracts decisions / action items / follow-ups into a structured JSON schema, then renders Slack-friendly markdown. Ships as a CLI, a FastAPI server, and a directory watcher: pick the surface that fits the team.

Next project

InfiniteCS Website

Need something like EchoScribe?

Tell me about it. I reply the same day.

Book a call