API playground
The API playground turns developer search traffic into implementation intent with sample requests, response schema, and modality-specific examples.
Report example
API response preview
- modality
- confidence
- evidence
- review_recommendation
Search intent
API playground conversion for developers
Primary evidence
Unified JSON schema, Webhook flow, Sample response
Recommended action
Use confidence scores with source context, policy thresholds, and human review.
Request examples
Developers should see how to submit text, image, audio, video, and code scans with a consistent API shape.
- Text request
- Image URL request
- Async video scan
- Webhook callback
Response examples
Response examples should include confidence, evidence, metadata, limitations, and reviewer explanation fields.
- Score
- Evidence
- Metadata
- Model version
Production rollout
API buyers need to understand latency, batch, async, privacy, and threshold behavior before integration.
- Batch scans
- Async jobs
- Zero retention
- Threshold tuning
Use cases
Developer evaluation
Enterprise proof-of-concept
API documentation conversion
Sample report preview
Media preview
Safe sample, redacted upload, or generated demonstration asset.
Public reports should only expose media that is lawful, consented, and safe to publish.
Confidence
200 OK
modality
Evidence item linked to score calibration, source context, and known uncertainty.
confidence
Evidence item linked to score calibration, source context, and known uncertainty.
evidence
Evidence item linked to score calibration, source context, and known uncertainty.
review_recommendation
Evidence item linked to score calibration, source context, and known uncertainty.
Evaluation table
| Criterion | What to check | Why it matters |
|---|---|---|
| Coverage | Text, image, audio, video, code. | Synthetic media risk rarely stays in one format. |
| Explainability | Score, indicators, timestamps, metadata, limitations. | Reviewers need evidence, not a black-box verdict. |
| Accuracy risk | False positives, false negatives, calibration. | High-impact workflows require documented uncertainty. |
| Workflow fit | API, batch, reports, retention, reviewer queues. | Search traffic must convert into a usable product path. |
Methodology and limitations
How to read the score
Detection output should be read as calibrated evidence. A high score means the observed signals are consistent with synthetic or manipulated media under the current model and sample conditions. It does not prove authorship, intent, or model attribution by itself.
Where review is required
Short samples, heavy editing, compression, translation, re-recording, mixed human-AI content, and unseen generators can reduce confidence. Use human review, source context, and policy thresholds before high-impact enforcement.
Next step
Match the action to the visitor intent: detector pages should lead to a scan, research pages to a downloadable report, enterprise pages to a demo, and developer pages to API keys or playground examples.
FAQ
Does the API support all modalities?
The platform is designed around a unified multimodal API for text, image, audio, video, and code.
Should video scans be synchronous?
Large media should usually use async processing and webhooks.
Can developers tune thresholds?
Enterprise workflows should support policy-specific thresholds and review bands.