# schibsted/WAAS

Whisper as a Service (GUI and API with queuing for OpenAI Whisper)

Repository: https://github.com/schibsted/WAAS
Canonical: https://ross.abutalabs.com/products/waas
Language: JavaScript
License: Apache-2.0
License Family: permissive
Last push: 2026-07-02T16:59:06+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 90, release rhythm 35, longevity 100
- inputs: {"age_days": 1420, "days_push": 62, "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 2075, forks 114 (observed 2026-08-28T04:06:10.728765+00:00)

## What it is
Whisper as a Service (WAAS) is a self-hosted GUI and API wrapper around OpenAI's Whisper speech-to-text model, with asynchronous job queuing and email/webhook callbacks. It includes a browser-based transcription editor for correcting segments and exporting SRT, text, or Jojo files.

## Use cases
- transcribe audio files to text with whisper
- generate srt subtitles from video or audio
- self-host a whisper transcription api with a queue
- translate audio to english text via whisper
- fix transcription errors in a browser editor
- batch transcribe files and get results by email

## When to choose
- you want a self-hosted whisper service with a web UI and async job queue
- you need subtitle (SRT) generation with human review/editing
- you want API access to transcription with webhook or email callbacks

## When to avoid
- you need real-time streaming transcription
- you prefer a managed cloud speech-to-text API without hosting
- you need speaker diarization or advanced audio analysis

## Facets
- artifact type: service
- maturity: active
- function: speech-recognition, api-framework, web-framework, gui, message-queue, webhook
- domain: speech-processing, self-hosted, apis, media
- platform: self-hosted, browser
- tags: whisper, transcription, asr, subtitles, srt, audio-to-text, queue-based-processing, natural-language-processing, web-server, docker

## Member repositories
- schibsted/WAAS (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:10.728765+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 2026-08-30T02:56:17.979157+00:00, confidence not recorded.
  - readme: https://github.com/schibsted/WAAS (fetched 2026-08-28T04:06:10.728765+00:00, sha ad4333d2ee12)
- Data as of 2026-08-30T08:39:29.467469+00:00.