Orukeet: a new shape for speech recognition
An open speech model for 25 languages, with fitted Gabor filters.
Speech-to-text, emotion, intent, tone of voice, meaning, sarcasm, and understanding.
Oruk is a research lab building speech foundation models and APIs for speech-to-text and speech emotion recognition. Work with words, speaker turns, tone, and emotion directly from audio, with models for recordings and live conversations.
Backed by
Research backgrounds
try resonance-1
r u ok? understand how things are said
Loading the recording…
Give your agent a better ear.
Let your agent pick up on hesitation, frustration, or excitement, then use that context to shape its response.
- Phrase-level emotion
- Conversation review
- Response design
Caller
“I’m not sure what to do next.”
worriedhesitant
Make room for a clearer explanation.
Illustrative workflow
Research highlights
All researchA voice. Many meanings.
Small differences in speech acquire meaning within communities.
Making Orukeet twice as fast
A faster Orukeet offshoot, with the accuracy tradeoff measured.
How a quantum memory learns what to connect
Past questions help a quantum memory choose which qubits to connect.
We taught a fruit fly to hear human emotion
A speech model built from 499 fruit fly neurons.
Speech models learn physics
Six speech systems learn the same filter shape, predicted by signal theory.
The shape of a voice
Speech models organize voices into shapes you can explore in 3-D.
Universal, with an accent
Emotion structure transfers across languages, with a measurable gap.
Teaching a speech model what counts as wrong
An almost-right transcript can reward the word it got wrong.
What is tone of voice?
Pitch, texture and timing contribute to overlapping impressions of a voice.
More audio. Less spend.
Prices in USD. Included minutes reset monthly.
Hobby
$9/ month
Billed monthly
- Speech understanding
- 250 min/month
- Transcription · Orukeet
- 20,000 min/month
7-day free trial
Start 7-day free trial of Hobby$0 today. Then $9/month. Cancel before the trial ends.
Builder
Recommended$49/ month
Billed monthly
- Speech understanding
- 2,500 min/month
- Transcription · Orukeet
- ≈ 109,000 min/month
7-day free trial
Start 7-day free trial of Builder$0 today. Then $49/month. Cancel before the trial ends.
Production
$199/ month
Billed monthly
- Speech understanding
- 20,000 min/month
- Transcription · Orukeet
- ≈ 442,000 min/month
7-day free trial
Start 7-day free trial of Production$0 today. Then $199/month. Cancel before the trial ends.
Enterprise
Contact us
Tailored to your team
- Speech understanding
- Custom
- Transcription · Orukeet
- Custom
How the two allowances work
Resonance 1, Fourier, Realtime, and Proficiency share the speech understanding allowance. Orukeet transcription has a separate allowance; optional tasks and request rounding reduce its estimated minutes. Allowances reset monthly. Trials include 25%; extra usage shares one spending cap.
Now serving: Resonance 2 — emotion and style on existing plans; new organizations need separate approval.
Benchmarks
Oruk at the top of the evaluations below.
Independently benchmarked bySpeko
Human speech
Emotion accuracy ↑
91%
1stby score- Oruk Resonance91%
- emotion2vec+ large88%
- qwen3-asr-flash65%
Synthetic speech
Emotion accuracy ↑
48%
1stby score- Oruk Resonance48%
- MERaLiON-SER-v133%
- Oruk Fourier33%
Oruk evaluationsPublished methods & results
Speech emotion
7-class accuracy ↑
77.8%
1stby score- Oruk Resonance 177.8%95% confidence interval 77.5 to 78.1
- emotion2vec+ seed68.7%95% confidence interval 68.3 to 69.1
- emotion2vec+ large68.6%95% confidence interval 68.2 to 69.0
Sarcasm
Macro-F1 × 100 ↑
56.2
1stby score- Oruk Resonance 156.295% confidence interval 52.4 to 60.1
- Deepgram nova-351.795% confidence interval 47.8 to 55.3
MUStARD · standard 5-fold
BeSimple leaderboard
Vocal Affect Bench
7-class accuracy ↑
49.3%
1stby score- Oruk Resonance 249.3%
- Gemini 3.8 Flash45.7%
- Gemini 3.5 Flash44.3%
Oruk trained on all 280 clips; not held out.
Talk to the people
behind the models.
Bring us your audio and your use case. We’ll help you find the right model and integration.
Build with Oruk
Send audio. Get a transcript, speaker turns, and vocal context.
Common questions
What exactly does Oruk do?
Oruk turns speech into transcripts, speaker turns, and labels for emotion and delivery. Choose a model for recorded audio or live conversations.
How is it different from speech-to-text?
Speech-to-text tells you what was said. Oruk also analyzes how it sounded: frustrated, excited, hesitant, sarcastic, and more.
What can I build with it?
Voice agents with more context, searchable call reviews, expressive captions, research tools, and other products that work with speech.
Can I try my own audio?
Yes. Open the full demo to use your microphone or upload a short recording. You can try it without an account.
Try your own audioDoes it work in real time?
Use Resonance 1 for a complete English recording: it returns a transcript, emotion and speaking-style labels, and timed segments. Use Realtime for live multilingual transcription with phrase-level emotion. Realtime is in preview and does not return the full file-analysis label set. Orukeet is an option for short English recordings or streamed utterances, with final text after commit.
Which languages and formats are supported?
Spectra-2 transcribes files in 25 languages; Realtime supports 32 locales. Original Resonance 1 and Fourier support English in WAV, FLAC, MP3, M4A, OGG, or WebM. Formats and limits vary by model. Transcription coverage does not establish emotion accuracy.
What happens to my recordings?
Resonance 2 buffers audio in memory until reset or session close and pending work finishes. Stored results exclude audio; 24-hour authorized replay is not a deletion deadline. Optional diarization keeps audio up to 48h and results up to 24h. Metadata is kept for billing, security and support. No training, fine-tuning or evaluation without explicit written agreement.
Data handlingHow accurate are the results?
Performance varies with the model, language, recording, and task. The benchmark report includes dated results, confidence intervals, and evaluation conditions. Emotion scores describe vocal expression, not someone’s inner state.
Read the evaluationsHow does pricing work?
Plans start at $9/month with a 7-day free trial. New organizations need separate approval for Resonance 2.
See pricing
