Build with oruk

01

Quickstart

Create a production key in the developer portal, set ORUK_API_KEY, and send a multipart request with an audio file. The example below returns transcript, emotion, style, segments, and usage in one response.

curl https://speech-api.oruk.ai/v1/audio/analysis \
  -H "Authorization: Bearer $ORUK_API_KEY" \
  -H "X-Request-ID: $(uuidgen)" \
  -F "model=oruk-resonance" \
  -F "file=@sample.wav"

{
  "id": "speech_8a3f...",
  "object": "speech.result",
  "task": "analysis",
  "model": "oruk-resonance",
  "text": "that is genuinely wonderful",
  "tagged_text": "that is genuinely wonderful <|happy|> <|warm|>",
  "language": "en",
  "duration": 2.84,
  "emotions": [{"label": "happy", "score": 0.94}],
  "styles": [{"label": "warm", "score": 0.81}],
  "segments": [],
  "usage": {
    "audio_seconds": 2.84,
    "billable_seconds": 2.84,
    "rate_per_minute_usd": "0.0120",
    "estimated_cost_usd": "0.000568",
    "pricing_version": "2026-07-11"
  }
}

02

Authentication

Send a bearer key on inference and model-catalog requests. Keys are shown only once. Never put a key in a URL.

03

Endpoints

All inference endpoints accept file and an optional model field as multipart/form-data.

Catalog and health routes: GET /v1/models, GET /v1/pricing, GET /livez, and GET /readyz.

04

Playground

Test any endpoint without leaving this page. Requests are sent straight from your browser to the API with your key, and the matching cURL command updates as you change the request.

curl https://speech-api.oruk.ai/v1/audio/analysis \
  -H "Authorization: Bearer $ORUK_API_KEY" \
  -H "X-Request-ID: $(uuidgen)" \
  -F "model=oruk-resonance" \
  -F "file=@sample.wav"

05

API reference

Every inference endpoint takes a multipart/form-data body with a required file and an optional model, and returns one speech.result envelope. The full machine-readable contract is in the OpenAPI schema.

{
  "id": "speech_...",          // unique result ID
  "object": "speech.result",
  "task": "analysis",          // transcription | emotion | style | affect | analysis
  "model": "oruk-resonance",
  "text": "...",               // transcript tasks only
  "tagged_text": "...",        // transcript with inline affect tags
  "language": "en",
  "duration": 2.84,            // measured seconds
  "emotions": [{"label": "happy", "score": 0.94}],
  "styles":   [{"label": "warm",  "score": 0.81}],
  "segments": [                // time-local outputs for longer audio
    {
      "id": 0, "start": 0.0, "end": 2.84,
      "text": "...", "tagged_text": "...",
      "words": [{"word": "...", "start": 0.0, "end": 0.4, "confidence": 0.99}],
      "emotions": [], "styles": []
    }
  ],
  "usage": {
    "audio_seconds": 2.84,
    "billable_seconds": 2.84,
    "rate_per_minute_usd": "0.0120",
    "estimated_cost_usd": "0.000568",
    "pricing_version": "2026-07-11"
  }
}

Transcript fields are only populated by transcription and analysis; emotion, style, and affect intentionally omit transcript text. Every response reports measured duration, billable duration, estimated cost, and pricing version in usage.

06

Multilabel output

A clip can return several emotions, several styles, or no selected style. At least one emotion is returned; the top emotion is the fallback when no score crosses its calibrated threshold. Use segment labels when affect changes over a longer recording.

07

Models

08

Pricing

USD per audio minute, billed by measured second with a one-second minimum. Pricing version 2026-07-11. Spectra 2 is a preview tier and is not yet serving traffic.

09

Audio

• WAV, FLAC, MP3, M4A, OGG, and WebM
• Mono or stereo input
• Common sample rates accepted
• English language in API v1
• 30 MB maximum upload
• 60 minute maximum duration

10

Errors and retries

Errors use one stable envelope and include the request ID. Retry 429, 500, 502, 503, and 504 with exponential backoff and jitter. Do not automatically retry other 4xx responses.

{
  "error": {
    "type": "invalid_request_error",
    "code": "audio_decode_failed",
    "message": "Audio could not be decoded.",
    "param": "file",
    "request_id": "req_6fc1..."
  }
}