oruk-ai Readyz API

openapi: 3.2.0
info:
  title: oruk Speech Readyz API
  version: 1.0.0
  description: HTTP file API for English transcription, emotion detection, speaking style, speech analysis, and speaking-proficiency scoring. Realtime is a separate multilingual WebSocket preview. Subscription models use plan minutes. Orukeet is an English preview included in every subscription at $0.00045 per audio minute ($0.027 per audio hour); optional tasks add their published rates. Orukeet usage.cost_microusd is usage valued at task rates, not an additional charge when covered by the monthly allowance. Only excess usage is billed. Existing credit-only accounts retain their credit balance. See https://oruk.ai/docs#orukeet and https://oruk.ai/pricing. Spectra-2 (oruk-spectra-2) adds 25-language transcription and 31 clip-level emotion/style scores through the main analysis and transcription routes. Uses shared speech understanding plan minutes. See https://oruk.ai/docs#spectra-2.
servers:
- url: https://speech-api.oruk.ai
  description: Production
security:
- bearerAuth: []
tags:
- name: Readyz
paths:
  /readyz:
    get:
      operationId: getReadiness
      summary: Inference readiness
      security: []
      responses:
        '200':
          description: Inference dependencies are ready
      tags:
      - Readyz
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: oruk API key
    HTTPBearer:
      type: http
      scheme: bearer
x-orukeet:
  model: oruk-orukeet
  billing_basis: subscription
  usd_per_audio_minute: '0.00045'
  optional_tasks:
    emotion_detection: '0.0080'
    diarize: '0.0040'
  max_audio_seconds: 60
  max_multipart_bytes: 4194304
  websocket_url: wss://orukeet-direct.oruk.ai/v1/audio/transcriptions/stream
  docs: https://oruk.ai/docs#orukeet
x-resonance-2:
  id: oruk-resonance-2
  availability: preview
  endpoint: /v1/audio/resonance-2
  documentation: https://oruk.ai/docs#resonance-2
  schema: https://oruk.ai/resonance-2.openapi.json
  pricing: Same shared plan minutes and legacy affect rate as Resonance 1.
x-spectra-2:
  model: oruk-spectra-2
  docs: https://oruk.ai/docs#spectra-2
  lifecycle: Stable
  supported_tasks:
  - transcription
  - analysis
  transcription_languages:
  - bg
  - hr
  - cs
  - da
  - nl
  - en
  - et
  - fi
  - fr
  - de
  - el
  - hu
  - it
  - lv
  - lt
  - mt
  - pl
  - pt
  - ro
  - ru
  - sk
  - sl
  - es
  - sv
  - uk
  language_details:
  - code: bg
    name: Bulgarian
  - code: hr
    name: Croatian
  - code: cs
    name: Czech
  - code: da
    name: Danish
  - code: nl
    name: Dutch
  - code: en
    name: English
  - code: et
    name: Estonian
  - code: fi
    name: Finnish
  - code: fr
    name: French
  - code: de
    name: German
  - code: el
    name: Greek
  - code: hu
    name: Hungarian
  - code: it
    name: Italian
  - code: lv
    name: Latvian
  - code: lt
    name: Lithuanian
  - code: mt
    name: Maltese
  - code: pl
    name: Polish
  - code: pt
    name: Portuguese
  - code: ro
    name: Romanian
  - code: ru
    name: Russian
  - code: sk
    name: Slovak
  - code: sl
    name: Slovenian
  - code: es
    name: Spanish
  - code: sv
    name: Swedish
  - code: uk
    name: Ukrainian
  language_detection: automatic
  min_audio_seconds: 0.045
  max_audio_seconds: 60
  max_file_bytes: 4194304
  max_multipart_bytes: 4210688
  sample_rate: 16000
  channels: 1
  formats:
  - wav
  - flac
  - pcm16
  - float32le
  score_scope: clip
  emotion_labels:
  - happy
  - excited
  - hopeful
  - sad
  - worried
  - angry
  - frustrated
  - disappointed
  - scared
  - disgusted
  - surprised
  - embarrassed
  - proud
  - relieved
  - neutral
  style_labels:
  - energetic
  - passionate
  - irritated
  - warm
  - playful
  - sarcastic
  - deadpan
  - hesitant
  - confident
  - sincere
  - skeptical
  - tired
  - formal
  - casual
  - impatient
  - distracted
  subscription_allowance: shared_audio_minutes
  minimum_billable_seconds: 1
  reference_usd_per_audio_minute:
    transcription: '0.0080'
    analysis: '0.0120'
  streaming:
    url: wss://speech-api.oruk.ai/v1/audio/spectra-2/stream
    authentication: Authorization bearer header from server clients
    input: mono 16 kHz PCM16 little-endian binary frames
    max_frame_bytes: 32768
    max_audio_seconds: 60
    finalization: explicit finish message
    output: one final Spectra2Result after finish
    provisional_results: false
    prepared_connection:
      session_endpoint: /v1/audio/sessions
      connection_endpoint: /v1/audio/stream-sessions
      lifetime_seconds: 30
      server_only: true
      recording_limit: Use max_audio_seconds from ready and finish before expires_at_ms.