NVIDIA NIM ASR API

openapi: 3.1.0
info:
  title: NVIDIA NIM Biology (BioNeMo) ASR 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: ASR
  description: Automatic speech recognition (speech-to-text)
paths:
  /v1/audio/transcriptions:
    post:
      summary: Transcribe Audio
      description: Transcribe a WAV/FLAC/MP3 audio clip into text using a Riva ASR NIM (e.g. Parakeet, Canary).
      operationId: createTranscription
      tags:
      - ASR
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
              - file
              - model
              properties:
                file:
                  type: string
                  format: binary
                model:
                  type: string
                  example: nvidia/parakeet-ctc-1.1b-asr
                language:
                  type: string
                  default: en-US
                response_format:
                  type: string
                  enum:
                  - json
                  - text
                  - srt
                  - vtt
                  default: json
                temperature:
                  type: number
      responses:
        '200':
          description: Transcription result.
          content:
            application/json:
              schema:
                type: object
                properties:
                  text:
                    type: string
                  language:
                    type: string
                  duration:
                    type: number
        '400':
          description: Invalid audio or model.
        '401':
          description: Missing or invalid API key.
components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: nvapi-...