RightNow AI Audio API

openapi: 3.1.0
info:
  title: RunInfra Audio API
  description: OpenAI-compatible HTTP API for verified RunInfra inference deployments.
  version: '2026-04-24'
  contact:
    name: RunInfra support
    email: jaber@runinfra.ai
    url: https://runinfra.ai/contact
servers:
- url: https://api.runinfra.ai/v1
  description: Production
security:
- bearerAuth: []
tags:
- name: Audio
paths:
  /audio/transcriptions:
    post:
      operationId: createTranscription
      summary: Transcribe audio
      description: Speech-to-text via Whisper-class models. Multipart upload with a non-empty audio file. Audio requests are sent once; do not rely on Idempotency-Key to deduplicate retries.
      tags:
      - Audio
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/TranscriptionRequest'
      responses:
        '200':
          description: Transcription
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Transcription'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '402':
          $ref: '#/components/responses/PaymentRequired'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
        '409':
          $ref: '#/components/responses/Conflict'
        '429':
          $ref: '#/components/responses/RateLimited'
        '500':
          $ref: '#/components/responses/InternalServerError'
        '502':
          $ref: '#/components/responses/BadGateway'
        '503':
          $ref: '#/components/responses/Unavailable'
        '504':
          $ref: '#/components/responses/GatewayTimeout'
  /audio/speech:
    post:
      operationId: createSpeech
      summary: Generate speech
      description: Text-to-speech served by XTTS, Bark, or Qwen3-TTS depending on the pipeline. Audio requests are sent once; do not rely on Idempotency-Key to deduplicate retries.
      tags:
      - Audio
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SpeechRequest'
      responses:
        '200':
          description: Audio bytes
          content:
            audio/mpeg:
              schema:
                type: string
                format: binary
            audio/wav:
              schema:
                type: string
                format: binary
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '402':
          $ref: '#/components/responses/PaymentRequired'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
        '409':
          $ref: '#/components/responses/Conflict'
        '429':
          $ref: '#/components/responses/RateLimited'
        '500':
          $ref: '#/components/responses/InternalServerError'
        '502':
          $ref: '#/components/responses/BadGateway'
        '503':
          $ref: '#/components/responses/Unavailable'
        '504':
          $ref: '#/components/responses/GatewayTimeout'
components:
  responses:
    BadGateway:
      description: Upstream serving backend transient failure
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    RateLimited:
      description: Rate limit exceeded
      headers:
        Retry-After:
          schema:
            type: integer
          description: Seconds to wait before retrying
        X-RateLimit-Remaining:
          schema:
            type: integer
          description: Remaining requests in the window
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Unavailable:
      description: Endpoint stopped, provisioning, or at capacity
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Forbidden:
      description: Key scope mismatch or plan limit exceeded
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    NotFound:
      description: Model or deployment not found
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Unauthorized:
      description: Missing or invalid API key
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Conflict:
      description: Idempotency conflict
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    GatewayTimeout:
      description: Gateway timeout
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    BadRequest:
      description: Malformed request
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    PaymentRequired:
      description: Insufficient credits
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    InternalServerError:
      description: Unexpected gateway error
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  schemas:
    TranscriptionRequest:
      type: object
      required:
      - file
      - model
      properties:
        file:
          type: string
          format: binary
          description: Non-empty audio file (mp3, wav, m4a, flac, webm, ogg).
        model:
          type: string
          example: whisper-large-v3
        language:
          type: string
          description: ISO-639-1 code
        prompt:
          type: string
        response_format:
          type: string
          enum:
          - json
          - text
          - srt
          - vtt
          - verbose_json
          default: json
        temperature:
          type: number
          default: 0
    Error:
      type: object
      properties:
        error:
          type: object
          required:
          - message
          - type
          properties:
            message:
              type: string
            type:
              type: string
            param:
              type: string
              nullable: true
            code:
              type: string
              nullable: true
    SpeechRequest:
      type: object
      required:
      - model
      - input
      properties:
        model:
          type: string
          example: kokoro
        input:
          type: string
        voice:
          type: string
        response_format:
          type: string
          enum:
          - mp3
          - wav
          - flac
          - opus
          - aac
          - pcm
          default: mp3
        speed:
          type: number
          default: 1
          minimum: 0.25
          maximum: 4
    Transcription:
      type: object
      properties:
        text:
          type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: RunInfra API key. Generate at https://runinfra.ai/settings/api-keys