Whisper ASR WebServices

This whisperasr provider allows to configure a transcription task to use the Whisper ASR WebService project.

const transcript = await transcribe("video.mp4", {
  model: "whisperasr:default",
});

This whisper service can run locally or in a docker container (see documentation).

CPU

docker run -d -p 9000:9000 -e ASR_MODEL=base -e ASR_ENGINE=openai_whisper onerahmet/openai-whisper-asr-webservice:latest

You can also override the transcription model alias to change the default model used by transcribe.

GitHub Actions

When running GenAIScript with whisper-asr in GitHub Actions, you need to set up the whisper-asr container as a service since the whisper-asr provider requires its own containerized service to function.

Service Container Configuration

Configure the whisper-asr service container in your workflow:

.github/workflows/transcription.yml

name: Transcription with Whisper ASR
on: [push, pull_request]

jobs:
  transcribe:
    runs-on: ubuntu-latest

    services:
      whisper-asr:
        image: onerahmet/openai-whisper-asr-webservice:latest
        ports:
          - 9000:9000
        env:
          ASR_MODEL: base
          ASR_ENGINE: openai_whisper
        options: >-
          --health-cmd "curl -f http://localhost:9000/health || exit 1"
          --health-interval 30s
          --health-timeout 10s
          --health-retries 5

    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-node@v4
        with:
          node-version: "22"

      - name: Run transcription script
        run: npx --yes genaiscript run transcript-script audio.wav
        env:
          WHISPERASR_API_BASE: http://whisper-asr:9000
          # Add your LLM provider secrets here
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

Environment Variables

Set the WHISPERASR_API_BASE environment variable to point to your whisper-asr service:

env:
  WHISPERASR_API_BASE: http://whisper-asr:9000