name: Deepgram Text-to-Speech API Capabilities
description: >-
  Capabilities exposed by Deepgram's Text-to-Speech API powered by the
  Aura model family.
capabilities:
  - name: Synthesize Speech
    description: Convert a text request into spoken audio.
    operationId: synthesizeSpeech
    method: POST
    path: /v1/speak
  - name: Stream Speech
    description: Stream synthesized speech as text arrives over WebSocket.
    operationId: streamSpeech
    method: WEBSOCKET
    path: /v1/speak
  - name: Choose Voice
    description: Select an Aura voice via the model parameter.
    operationId: selectVoice
    method: POST
    path: /v1/speak
use_cases:
  - name: Voice agents and IVR
    description: Power conversational voice agents and interactive voice response systems.
  - name: Accessibility
    description: Read web pages, articles, and notifications aloud for accessibility.
  - name: Voicebot prompts
    description: Generate dynamic spoken prompts in chatbots, kiosks, and devices.
  - name: Audio content production
    description: Produce narration for podcasts, videos, and training material.