# SevaSk/ecoute

Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox.

Repository: https://github.com/SevaSk/ecoute
Canonical: https://ross.abutalabs.com/products/ecoute
Homepage: https://github.com/SevaSk/ecoute
Language: Python
License: MIT
License Family: permissive
Topics: gpt-35-turbo, whisper-ai, windows
Last push: 2026-04-08T23:39:42+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 76, release rhythm 35, longevity 86
- inputs: {"age_days": 1214, "days_push": 147, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6047, forks 830 (observed 2026-08-28T04:09:34.593237+00:00)

## What it is
Ecoute is a live transcription application that captures audio from both the user's microphone and speakers and displays real-time transcripts in a textbox. It uses Whisper (locally or via OpenAI API) for transcription and optionally GPT-3.5 Turbo to suggest responses during conversations.

## Use cases
- transcribe live conversations in real time
- get live captions for both my microphone and system audio
- get real-time suggested replies during calls
- transcribe meeting audio on Windows
- live speech-to-text using Whisper

## When to choose
- you are on Windows and want real-time transcripts of both mic and speaker audio
- you want optional GPT-powered response suggestions during conversations
- you prefer a lightweight Python tool with local Whisper support

## When to avoid
- you need cross-platform support (only tested on Windows)
- you need accurate speaker diarization with names for meetings
- you want a production-ready or actively developed transcription solution

## Facets
- artifact type: application
- maturity: maintenance
- function: speech-recognition, audio-processing, llm-inference
- domain: speech-processing, artificial-intelligence, developer-tools
- platform: windows, python
- tags: live-transcription, whisper, real-time-captions, microphone-and-speaker, gpt-3-5-turbo, desktop

## Member repositories
- SevaSk/ecoute (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:34.593237+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:48:56.806979+00:00, confidence not recorded.
  - readme: https://github.com/SevaSk/ecoute (fetched 2026-08-28T04:09:34.593237+00:00, sha 5e086fbe7353)
  - homepage: https://github.com/SevaSk/ecoute (fetched 2026-08-29T08:45:11.664637+00:00, sha 1439e853e991)
- Data as of 2026-08-30T08:39:29.467469+00:00.