Skip to content
oruk
Try the API

Speech to Text API

Speech-to-Text API with Emotion Detection

Accurate English transcription with word timings from one REST call. Send the same audio to unified analysis to return emotion and speaking-style labels with the transcript — the words, and how they were said.

$50 trial credit · No card · Transcription from $0.0045 per audio minute

Create your account

$50 trial credit · No card · Sign up, then create a key.

Already have an account? Sign in

curl https://speech-api.oruk.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $ORUK_API_KEY" \
  -F file=@call.wav -F model=oruk-spectra-1
{
  "model": "oruk-spectra-1",
  "text": "thanks for calling, how can I help",
  "segments": [{ "start": 0.0, "end": 2.9,
    "words": [{ "word": "thanks", "start": 0.0, "end": 0.4 }] }],
  "usage": { "audio_seconds": 42.7, "estimated_cost_usd": 0.0032 }
}

Measured accuracy, stated with caveats

English word error rate averaged across four public test sets (LibriSpeech clean/other · Common Voice · TED-LIUM). Lower is better. Rows marked published are the vendor’s own reported numbers, not runs in our harness:

SystemWERSource
oruk Spectra4.44%Measured
Open ASR A4.47%Measured
Azure Speech-to-Text5.5%Published
Whisper Large V35.7%Published
Whisper Medium6.1%Published

Full leaderboard, evaluation snapshot, and protocol on the benchmarks page.

Transcribe your audio

$50 trial credit. No card required.

The transcript is half the signal

“Great, thanks.” transcribes identically whether the delivery sounds warm or sarcastic. A plain transcription response stops at the words. Send the file to /v1/audio/analysis and the response adds 15 calibrated emotion scores, 16 speaking-style scores, and an inline-tagged transcript — no second vendor, no pipeline glue:

"text":        "great, thanks",
"tagged_text": "great, thanks <|frustrated|> <|sarcastic|>",
"emotions":    [{ "label": "frustrated", "score": 0.83 }],
"styles":      [{ "label": "sarcastic",  "score": 0.78 }]

Plain transcription stays $0.0045/min; the unified analysis call is $0.0090/min. Both are metered per measured second. Rates on the pricing page.

Transcribe your audio

$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.

Prerecorded files, not live captions
This API transcribes audio files. If you need live captioning, dictation, or real-time subtitles, this is not the product.
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.
Transcribe your audio

$50 trial credit. No card required.

Start with $50 in trial credit

Create an account, verify your email, and make your first request in minutes. No card required.

Transcribe your audioRead the docs