Reality Defender's audio detection analyzes speech content using multiple models to identify signs of AI generation or manipulation. Each audio file receives a single overall judgement and score, produced by combining signals across models that ran on that content.
What's included in audio analysis
Audio detection includes signals from three individual models, combined by an ensemble:
rd-everest-aud (Advanced) — uses general-purpose embeddings that discriminate synthetic from real human speech.
rd-marconi-aud (Foundational) — uses embeddings from Reality Defender’s proprietary encoder, trained to learn deepfake artifacts directly rather than adapted from general speech models.
rd-slim-aud (Generalizable) — uses mismatch in style and linguistic patterns that are otherwise unique to real human speech.
All three models contribute to a single rd-aud-ensemble score, which represents the combined assessment of manipulation likelihood for the file.
What you'll see in the API response
Each model returns its own result in the models[] array, including a status, finalScore, and predictionNumber. The top-level resultsSummary contains the overall verdict and aggregated score.
Models that are not applicable to a given media type (for example, video or image models on an audio file) will return "status": "NOT_APPLICABLE" with null score fields. This is expected behavior.
For scans that cannot return a standard result, the API may include additional status or reason fields that explain why the media could not be fully evaluated. For the full response schema and supported reason values, see the Get Media Detail API reference.
How to interpret audio model results
The three models use different approaches to detect synthetic speech. Divergence between them is expected: one model may detect manipulation that the others do not, depending on how the audio was generated. The ensemble accounts for this, combining all three signals into a single calibrated score.
Audio models analyze content in 3-second segments, with an aggregation model producing the final decision for the full file. The score you receive reflects the aggregated assessment across the entire audio.
For most use cases, the overall audio judgement and score in resultsSummary should be used as the primary decision signal. Individual model results are available for debugging, auditing, or deeper investigation.