# joshnewlan/say_what

Using speech-to-text to fully check out during con calls

Repository: https://github.com/joshnewlan/say_what
Canonical: https://ross.abutalabs.com/products/say_what
Language: Python
License Family: other
Last push: 2019-02-12T19:01:09+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3760, "days_push": 2759, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2087, forks 117 (observed 2026-08-28T04:06:12.003106+00:00)

## What it is
A Python script that listens to conference call audio via speech-to-text (IBM Watson) and alerts the user on HipChat when their name is mentioned, including a transcript of surrounding context. It also plays a canned 'sorry, I was on mute' audio clip as a humorous cover.

## Use cases
- get notified when my name is said during a conference call
- transcribe meeting audio and search for keywords
- monitor conference calls for my name using speech recognition
- catch up on what was said right before I was mentioned in a meeting
- build a keyword-spotting alert system on live microphone audio

## When to choose
- you want a hackable Python starting point for live speech-to-text keyword alerts
- you already use Splunk and HipChat and want to integrate audio monitoring with them

## When to avoid
- you need a maintained or supported tool - it depends on defunct services (HipChat, old IBM Bluemix) and hasn't been updated since 2019
- you need production-grade meeting transcription or a cross-platform solution
- you want something that works out of the box without significant reconfiguration

## Facets
- artifact type: application
- maturity: abandoned
- function: speech-recognition, nlp, monitoring, alerting
- domain: speech-processing, developer-tools
- platform: python, cli
- tags: speech-to-text, conference-calls, ibm-watson, hipchat, splunk, novelty-project, natural-language-processing, automation, macos

## Member repositories
- joshnewlan/say_what (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:12.003106+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 2026-08-30T02:55:45.296293+00:00, confidence not recorded.
  - readme: https://github.com/joshnewlan/say_what (fetched 2026-08-28T04:06:12.003106+00:00, sha c25cc6239165)
- Data as of 2026-08-30T08:39:29.467469+00:00.