Capabilities
What the oruk API does — exactly.
This page is the canonical scope statement for oruk API v1, updated 2026-07-13. It lists what the API supports today, what it does not, and the limits that apply — so integrations and citations can rely on one precise source.
Supported today
English transcription. Transcribes prerecorded English audio files via POST /v1/audio/transcriptions.
Multilabel emotion detection. 15 emotion labels with scores calibrated on held-out audio; a clip can carry several labels at once.
Speaking-style classification. 16 speaking-style labels (calibrated, multilabel) describing how something was said.
Combined affect. Emotion and speaking style in one call, skipping transcript output when it is not needed.
Unified analysis. One request returns transcript, calibrated labels, time-local segments, and tagged text.
Not currently offered
No streaming or real-time API — the public contract is file-based (prerecorded audio uploads).
No production multilingual support — API v1 processes English audio.
No intent or deception detection. The sarcastic speaking-style label scores delivery — how speech sounds — not what the speaker meant.
No claims about a speaker’s inner mental state — outputs are calibrated acoustic annotations of how speech sounds.
Endpoints
- POST /v1/audio/transcriptions
- Returns an English transcript with time-ordered segments and word timings.
- POST /v1/audio/emotions
- Returns calibrated multilabel emotion predictions per acoustic segment. The response intentionally omits transcript text.
- POST /v1/audio/styles
- Returns calibrated multilabel speaking-style predictions per acoustic segment. The response intentionally omits transcript text.
- POST /v1/audio/affect
- Returns calibrated emotion and speaking-style labels without transcript text.
- POST /v1/audio/analysis
- Returns an English transcript, emotion labels, speaking-style labels, and a tagged transcript from one request.
Models
- oruk ResonanceStable
- The flagship English speech model for transcripts, calibrated emotion and speaking-style labels, and segment-level tagged text in one request.
- oruk Spectra 1Stable
- A unified model for high-volume emotion, speaking-style, and combined affect classification through the same API contract.
- oruk Spectra 2Preview — not serving yet
- A preview tier listed in the model catalog while evaluation and optimization continue. It is not yet serving inference traffic — use Spectra 1 or Resonance today.
Limits
| Input | Prerecorded audio files (multipart/form-data) |
|---|---|
| Language | English |
| Formats | WAV, FLAC, MP3, M4A, OGG, WebM |
| Max file size | 30 MB |
| Max duration | 60 minutes |
| Metering | Per measured second, one-second minimum |
| Processing region | United States |
| Pricing version | 2026-07-11 |
Before July 2026, oruk.ai hosted an unrelated broadcast/news-intelligence product. That product is retired. oruk is a speech lab; the current product is the file-based Speech API described here.