NVIDIA NIM · OpenAPI Overlay 1.0.0

API Evangelist conversational phrasing for NVIDIA NIM Speech TTS API

2 actions 2 updates phrasing extends openapi/nvidia-nim-tts-api-openapi.yml
Generated by API Evangelist Written by API Evangelist tooling for NVIDIA NIM's API. It is a proposal applied on top of the contract, not a document NVIDIA NIM publishes.
View Overlay File View on GitHub Overlay Specification

What the actions change

x-apievangelist-phrasing

Targets 2

$.info
$.paths['/v1/audio/speech'].post

OpenAPI Overlay

Raw ↑ 
# Generated by API Evangelist (build-phrasing.py). Our phrasing, not observed demand.
overlay: 1.0.0
info:
  title: API Evangelist conversational phrasing for NVIDIA NIM Speech TTS API
  version: 1.0.0
extends: openapi/nvidia-nim-tts-api-openapi.yml
actions:
- target: $.info
  update:
    x-apievangelist-phrasing:
      method: generated
      generated: '2026-10-01'
      generator: build-phrasing.py
      label: Generated by API Evangelist
      operations: 1
- target: $.paths['/v1/audio/speech'].post
  update:
    x-apievangelist-phrasing:
      intent: Synthesize speech audio from text
      effect: write
      questions:
      - Can I convert a paragraph of text into a spoken WAV or MP3 file with Magpie-TTS or FastPitch?
      - Is it possible to choose the voice and speaking speed when generating text-to-speech audio?
      - Which audio formats can synthesized speech be returned in?
      instructions:
      - text: Read the text {input} aloud with the {voice} voice on the {model} text-to-speech model.
        slots:
          input: requestBody.input
          voice: requestBody.voice
          model: requestBody.model
      - text: Synthesize {input} as {response_format} audio using {model} and voice {voice}.
        slots:
          input: requestBody.input
          response_format: requestBody.response_format
          model: requestBody.model
          voice: requestBody.voice
      - text: Generate speech for {input} with {model} voice {voice}, spoken at {speed} speed.
        slots:
          input: requestBody.input
          model: requestBody.model
          voice: requestBody.voice
          speed: requestBody.speed
      method: generated
      generated: '2026-10-01'