Generate full songs with vocals, lyrics, and instrumentals from text prompts in minutes.
oruk
$9Starting price
1.4KMonthly visits
2Popularity
About oruk
A speech API that processes English audio to return transcripts, emotion labels, and speaking-style classifications in a single call. It supports three main tasks: transcription, emotion detection with 15 calibrated labels, and speaking-style classification with 16 labels. The API can return unified analysis combining all outputs or focus on specific aspects like emotion and style without transcript generation. Models include Resonance for high-accuracy transcription and unified analysis, Spectra 1 for efficient emotion and style workloads, and Spectra 2 as a preview tier. Billing is based on measured audio duration with no platform fees, and a $50 trial credit is available without requiring a payment method. The service emphasizes calibrated multilabel outputs and time-local segments for tracking changes over time in long audio.
Key features
- English transcription
- 15 emotion labels with calibrated scores
- 16 speaking-style labels
- Unified analysis combining transcript, emotion, and style
- Multilabel outputs allowing multiple labels per clip
- Time-local segments for segment-level analysis
- Affect endpoint for emotion and style without transcript
- Measured duration and cost reporting per response
Use cases
- Customer support call analysis with emotion and style detection
- Voice assistant integration with unified transcript and affect outputs
- Media content moderation using speaking-style and emotion labels
Pros
- Returns transcripts, emotion, and speaking-style in one API call
- Calibrated multilabel scores for emotion and style
- Billed by measured audio duration with no platform fees
- $50 trial credit available without payment method
- Supports unified analysis combining all outputs
Cons
- English-only transcription support
- API v1 uses file-based processing, not streaming
- Spectra 2 preview tier not yet serving inference traffic
- No public pricing for on-device licensing
Frequently asked questions about oruk
What does the oruk API do today?
The oruk API processes English audio files to provide transcription, emotion detection with 15 calibrated labels, speaking-style classification with 16 labels, or unified analysis combining all outputs in a single call.
Who is the oruk API designed for?
The API is built for developers and teams building conversational AI applications who need accurate speech understanding, including transcriptions, emotion, and speaking-style analysis, without managing multiple systems.
How does the billing model work for oruk?
Billing is based on measured audio duration in seconds, with no platform fees. A $50 trial credit is available without requiring a payment method, and volume rates are available for larger usage.
What models does oruk offer?
The API currently offers two public models: Spectra 1 for efficient emotion and style workloads, and Resonance for high-accuracy transcription and unified analysis. Spectra 2 is listed as a preview tier but is not yet serving traffic.
Does oruk support streaming audio input?
No, the current public API contract is file-based and does not support streaming audio input.
How can I get started with the oruk API?
Users can join the waitlist to access the API, review the quickstart guide, and explore live demos on the website to evaluate the service before integrating it into their applications.
oruk Website Engagement
Last Update: 9 days ago
Total Monthly Visits
0
Bounce Rate
—
Visit Duration (avg)
—
Pages Per Visit
—
Country Rank
—
Unknown
Global Rank
0
