oruk 0.1.0

Official Python client for the oruk Speech API: English transcription, calibrated multilabel emotion and speaking-style labels, and unified audio analysis.

oruk — Python client for the oruk Speech API

Official Python SDK for oruk, the speech lab building audio models for English transcription, calibrated multilabel emotion detection, speaking-style classification, and unified audio analysis.

The API is file-based: send a prerecorded English audio file (WAV, FLAC, MP3, M4A, OGG, or WebM; up to 30 MB / 60 minutes), get structured results back. Usage is metered per second of audio.

Install

pip install oruk

Quickstart

Create an account at oruk.ai ($5 trial credit, no card required) and create an API key in the developer portal.

import os
from oruk import Oruk

with Oruk(api_key=os.environ["ORUK_API_KEY"]) as client:
    result = client.analyze("sample.wav", model="oruk-resonance")

print(result["text"])       # English transcript
print(result["emotions"])   # calibrated multilabel emotion scores
print(result["styles"])     # calibrated multilabel speaking-style scores

Endpoints

Method	API endpoint	Returns
client.transcribe(file)	POST /v1/audio/transcriptions	English transcript
client.emotions(file)	POST /v1/audio/emotions	15 calibrated emotion labels
client.styles(file)	POST /v1/audio/styles	16 calibrated speaking-style labels
client.affect(file)	POST /v1/audio/affect	emotion + style, no transcript
client.analyze(file)	POST /v1/audio/analysis	transcript, labels, segments, tagged text

Every method accepts a path, Path, or binary file object, plus optional model= (oruk-resonance, oruk-spectra-1) and request_id= arguments.

The client sends a unique request ID per call and retries only 429 and transient 5xx responses with jittered backoff. Errors raise OrukAPIError with status, code, and request_id attributes.

Links

• Documentation and API reference: https://oruk.ai/docs
• Capabilities and scope: https://oruk.ai/capabilities
• Pricing: https://oruk.ai/pricing
• Benchmarks: https://oruk.ai/benchmarks/methodology
• Service status: https://oruk.ai/status

License

MIT