oruk-ai Models API
The Models API from oruk-ai — 2 operation(s) for models.
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/oruk-ai:oruk-ai-models-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
OpenAPI Specification
openapi: 3.2.0
info:
title: oruk Speech Models 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: Models
paths:
/v1/models:
get:
operationId: listModels
summary: List public models and supported tasks
responses:
'200':
description: Model catalog
content:
application/json:
schema:
type: object
default:
$ref: '#/components/responses/Error'
tags:
- Models
/v1/models/oruk-resonance-2/access:
get:
summary: Read organization Resonance-2 access
operationId: getResonance2Access
security:
- HTTPBearer: []
responses:
'200':
description: Organization model access status
content:
application/json:
schema:
type: object
required:
- model
- status
- approved
properties:
model:
type: string
const: oruk-resonance-2
status:
type: string
enum:
- not_requested
- pending
- approved
- denied
- revoked
approved:
type: boolean
request_access_url:
type: string
format: uri
'401':
description: Invalid API key
tags:
- Models
post:
summary: Request Resonance-2 access
operationId: requestResonance2Access
security:
- HTTPBearer: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- use_case
properties:
use_case:
type: string
minLength: 10
maxLength: 2000
responses:
'200':
description: Organization model access status
content:
application/json:
schema:
type: object
required:
- model
- status
- approved
properties:
model:
type: string
const: oruk-resonance-2
status:
type: string
enum:
- not_requested
- pending
- approved
- denied
- revoked
approved:
type: boolean
request_access_url:
type: string
format: uri
'202':
description: Organization model access status
content:
application/json:
schema:
type: object
required:
- model
- status
- approved
properties:
model:
type: string
const: oruk-resonance-2
status:
type: string
enum:
- not_requested
- pending
- approved
- denied
- revoked
approved:
type: boolean
request_access_url:
type: string
format: uri
'400':
description: Invalid use case or JSON
'401':
description: Invalid API key
'413':
description: Body exceeds 12 KB
'415':
description: Requires application/json
'429':
description: Too many requests
tags:
- Models
components:
responses:
Error:
description: Stable error envelope
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorEnvelope'
schemas:
ErrorEnvelope:
type: object
required:
- error
properties:
error:
type: object
required:
- type
- code
- message
properties:
type:
type: string
code:
type: string
message:
type: string
param:
type:
- string
- 'null'
request_id:
type:
- string
- 'null'
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.