Speech & Audio

{
  "id": "speech_audio",
  "category_id": "processing",
  "title": [
    {
      "locale": "en",
      "value": "Speech & Audio"
    }
  ],
  "description": [
    {
      "locale": "en",
      "value": "AI systems that convert between spoken words and other formats, or that classify non-speech sound. Includes speech-to-text (transcription), text-to-speech (synthetic voice), keyword spotting, and audio event detection. Voice-as-identity (recognizing who is speaking) belongs in Biometric Recognition."
    }
  ],
  "authoring_guidance": [],
  "examples": [],
  "sources": [],
  "symbol_id": "processing_text-to-speech",
  "variables": [
    {
      "id": "additional_description",
      "label": [
        {
          "locale": "en",
          "value": "Description"
        }
      ],
      "required": false
    }
  ],
  "shape": "circle",
  "icon_variants": [
    "default",
    "dark"
  ]
}