Audio Event Detection

Audio Event Detection scores an audio file against a fixed vocabulary of 42 non-speech sound events: instruments, human vocalizations such as laughter and coughing, and environmental noises such as a knock or a gunshot. It returns a probability for each event it confidently detected, plus the duration of the processed audio. It is a pure classification endpoint, producing no transcript, diarization, or PII/PHI tagging.

	Batch
Use case	Detect which non-speech sound events are present in an audio file
Protocol	HTTP POST
Max file size	100 MB
Output	A probability per detected event, plus `duration_ms`
Options	None. Only `upload_file` is accepted

probs carries one entry per confidently detected event, drawn from a vocabulary of 42, and is an empty object when nothing was detected. Entries are independent probabilities: they are not mutually exclusive and are not expected to sum to 1, so each is thresholded on its own. An omitted event was not detected with sufficient confidence, which is not the same as it being absent from the audio. See Audio Event Detection. For a side-by-side comparison with the other Modulate capabilities, see Which API should I use?.

Authentication

Uses the X-API-Key header. See Authentication and rate limits.

Velma

Speech-to-text Transcription

Deepfake Detection

Emotion Detection

Accent Detection

PII/PHI Redaction

Music Detection

AI Music Detection

Language Detection