openapi: 3.1.0
info:
  title: NVIDIA NIM Biology (BioNeMo) ASR TTS API
  description: 'NVIDIA BioNeMo NIMs for drug discovery and structural biology. Each model is a containerized microservice with its own task-specific payload but a consistent JSON contract. Includes protein structure prediction (AlphaFold2, ESMFold, OpenFold), protein generation (ProtGPT2, RFDiffusion), molecular property prediction (MolMIM), small molecule generation, and molecular docking (DiffDock).

    '
  version: '2026-05-25'
  contact:
    name: NVIDIA Developer Support
    url: https://forums.developer.nvidia.com/c/ai-data-science/nemo-llm-service/
  license:
    name: NVIDIA AI Enterprise License
    url: https://www.nvidia.com/en-us/data-center/products/ai-enterprise/
servers:
- url: https://integrate.api.nvidia.com
  description: NVIDIA-hosted NIM endpoint
- url: http://localhost:8000
  description: Self-hosted NIM container default
security:
- BearerAuth: []
tags:
- name: TTS
  description: Text-to-speech synthesis
paths:
  /v1/audio/speech:
    post:
      summary: Synthesize Speech
      description: Generate WAV/MP3 audio from text using a Riva TTS NIM (e.g. Magpie-TTS, FastPitch).
      operationId: createSpeech
      tags:
      - TTS
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - model
              - input
              - voice
              properties:
                model:
                  type: string
                  example: nvidia/magpie-tts
                input:
                  type: string
                  description: Text to synthesize.
                voice:
                  type: string
                  example: en-US.Female-1
                response_format:
                  type: string
                  enum:
                  - mp3
                  - wav
                  - opus
                  - flac
                  default: mp3
                speed:
                  type: number
                  default: 1.0
      responses:
        '200':
          description: Synthesized audio bytes.
          content:
            audio/mpeg:
              schema:
                type: string
                format: binary
            audio/wav:
              schema:
                type: string
                format: binary
        '400':
          description: Invalid request.
        '401':
          description: Missing or invalid API key.
components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: nvapi-...