v1

latestOpenAPI 3.1.02026-08-04118425322.0 KB

search > search

Audio Search

Find video segments where the spoken content matches a natural-language query. Use this to find moments by what was said, for example, thank you for your time or breaking news.Returns matching audio segments with the parent video, the transcript text, and timestamps so you can jump straight to the moment.

post/api/v1/search/audio

Headers

Authorizationstring required

Bearer authentication

Request body

dataset_idstring uuid required

The unique identifier for the dataset

offsetinteger

Starting index to return

limitinteger

Max number of items to return

moderation_score_type'probability' | 'level'

Score type returned by the moderation service.

PROBABILITY: Scores in range 0-1 (uses BGE Reranker model)
LEVEL: Scores in range 0-5 (uses OpenAI model)

text_querystring required

The text query to search for

skip_moderationboolean

Skip content moderation if enabled

Response

Successful Response