Skip to main content
stub Cyberwave exposes speech-to-text as an MLModel, not as a ROS intelligence layer. Audio goes in, a JSON transcript comes out, and the same model can be called from POST /api/v1/mlmodels/{uuid}/run or a workflow CALL_MODEL node. The default catalog model is Whisper Large v3: 
{
  "audio_url": "https://example.com/audio.wav",
  "language": "auto",
  "task": "transcribe"
}
The Whisper Cloud Node returns: 
{
  "text": "...",
  "segments": [],
  "language": "en"
}
Use this when a microphone driver uploads audio and a workflow needs to pass the transcript into a downstream controller policy, planner, or human-in-the-loop step.