Analytics on how the call sounded
Most AI call analytics starts and ends with the transcript, so identical words spoken calmly or furiously score the same. oruk measures the audio: each time-local segment carries its own calibrated emotion and speaking-style scores, so a call reads as an arc — where frustration climbed, where it settled, and which sentence sat at the turn. That is the signal QA rubrics, coaching, and escalation analytics are usually missing.
Where teams apply it
The same endpoint backs several call-analytics programs, each covered in depth on its own page: contact center analytics for queue-wide scoring and QA, voice of customer analytics for trending how customers sound over time, sales call analysis for coaching against specific moments in a deal, and voice call sentiment analysis for the per-sentence sentiment arc itself.
Measured in the open, stated with caveats
speech-emotion-bench
77.6% accuracy
Top measured result in our July 2026 release. Open models use the full 64,384 held-out clips; closed/API and audio-LLM systems use a fixed 5,000-clip subset. The highest-scoring non-oruk row is emotion2vec+ seed at 68.7%. The caveat, stated plainly: the oruk entry is trained in-distribution while other systems are evaluated zero-shot. Protocol and downloadable results are on the methodology page.
What a response means
A score of 0.83 for frustrated means the audio crossed a threshold calibrated on held-out speech — it describes how the clip sounds, not what the speaker meant or felt inside. Scores are probabilistic acoustic signals and should never be the sole basis for a consequential decision.
Try it yourself first: run the live analyzer on your own voice, no account needed.
Data handling: audio and outputs are used to produce the response and are not retained after it is returned; oruk never trains on customer content. Full commitments in the privacy policy.
$50 trial credit. No card required.
Exactly what you are buying
The limits below are stated here so you do not discover them after integrating.
- Post-call, not live agent assist
- The API analyzes completed recordings. Real-time call monitoring and live agent assist are out of scope for API v1.
- Input
- Prerecorded English audio files only. No production multilingual support in API v1.
- No real-time streaming
- The public contract is file-based. You upload a file and get the full result back; there is no websocket or streaming endpoint.
- File limits and formats
- Up to 30 MB and 60 minutes per file. WAV, FLAC, MP3, M4A, OGG, and WebM are supported.
- Request behavior
- Synchronous REST: one POST, one response. Every response reports its measured duration and estimated cost.
- Pricing
- Emotion on Spectra 1 costs $0.0060 per audio minute (pricing version 2026-07-11), metered per measured second with a one-second minimum. Full rates on the pricing page.
- Data retention and training
- Audio and outputs are not retained after the response is returned; billing and audit metadata is kept. oruk never trains on customer content.
- What scores are — and are not
- Emotion scores are probabilistic acoustic signals calibrated on held-out audio. They are not intent, truth, medical, employment, or psychological judgments, and must not be the sole basis for consequential decisions. See responsible use.
- Model and version stability
- Models are versioned; Spectra 1 and Resonance are stable, Spectra 2 is in preview. Changes are announced on the changelog.
- Support
- Email access@oruk.ai; the production guide covers retries, limits, and error handling.
$50 trial credit. No card required.
An API, not another dashboard
Underneath, this is one call to the emotion recognition API with transcription included. Integrate it from the API docs in a few lines of Python or TypeScript, or hear it first in the captioning demo.
$50 trial credit. No card required.
Frequently asked questions
- What is AI call analytics?
- AI call analytics uses machine learning to turn recorded calls into structured data: what was said, who sounded how, and where the conversation turned. The oruk Speech API returns a transcript plus calibrated emotion and speaking-style scores for each sentence of a recording, so analytics can be built on how the call sounded, not just its words.
- How is this different from call center analytics software?
- Products like Gong or Observe.ai sell a packaged application for one team. oruk is the API layer underneath: you send audio, get JSON back, and build the dashboard, QA workflow, or CRM integration your team actually needs. If you want software you log into, buy a product; if you are building one, use the API.
- Does it work in real time during a call?
- No. API v1 is file-based: you upload a completed recording and receive the full result synchronously. There is no streaming endpoint, so it fits post-call scoring, coaching, and quality review rather than live agent assist.
- What audio does it accept?
- Prerecorded English audio in WAV, FLAC, MP3, M4A, OGG, or WebM, up to 30 MB or 60 minutes per file. Pricing is metered per measured second, and new accounts include $50 in trial credit.
- What signals come back for each call?
- POST /v1/audio/analysis returns the transcript, 15 calibrated multilabel emotion scores, 16 speaking-style scores, time-local segments with their own labels, a tagged transcript, and usage metadata with the measured seconds and estimated cost.
Start with $50 in trial credit
Create an account, verify your email, and make your first request in minutes. No card required.