Text to Transcript (with Metadata Filters) | Coactive AI

Triggers an asynchronous transcript search within the specified dataset (dataset_id), restricted to videos whose metadata matches every entry in metadata_filters (e.g., rating = PG, genre = documentary). When match_mode="semantic", the text_query is encoded with the dataset’s configured audio/transcript encoder (e.g., sentence transformers, Qwen) and ranked against transcript embeddings via vector similarity. When match_mode="exact", no embedding is computed and the raw text_query is matched lexically against transcript text. Returns the Databricks run_id immediately; use the status and result endpoints to poll for the final ranked list of transcript segments (each with the parent video, audio segment, timestamp, score, coverage score, and optional moderation score).

Triggers an asynchronous transcript search within the specified dataset (`dataset_id`), restricted to videos whose metadata matches every entry in `metadata_filters` (e.g., `rating = PG`, `genre = documentary`). When `match_mode="semantic"`, the `text_query` is encoded with the dataset's configured audio/transcript encoder (e.g., sentence transformers, Qwen) and ranked against transcript embeddings via vector similarity. When `match_mode="exact"`, no embedding is computed and the raw `text_query` is matched lexically against transcript text. Returns the Databricks `run_id` immediately; use the status and result endpoints to poll for the final ranked list of transcript segments (each with the parent video, audio segment, timestamp, score, coverage score, and optional moderation score).

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Request

This endpoint expects an object.

dataset_idstringRequiredformat: "uuid"

Dataset to search within

text_querystringRequired>=2 characters

Query text matched against transcripts. In semantic mode it is encoded into an embedding and ranked via vector similarity; in exact mode it is matched lexically without embedding.

limitintegerOptional1-100Defaults to 40

Max number of results to return

offsetintegerOptional>=0Defaults to 0

Number of results to skip before returning

metadata_filterslist of objectsOptional

List of filter objects applied against asset metadata fields before scoring. All filters are combined with AND.

skip_moderationbooleanOptionalDefaults to false

When true, moderation scoring is skipped and moderation_score will be null on all results.

match_modeenumOptional

semantic: encode query with the dataset audio/transcript encoder; exact: pass text to the job without embedding for literal phrase matching.

Allowed values:

Response

Successful Response

run_idinteger

Databricks job run ID to use for status polling and result retrieval

Errors

422

Unprocessable Entity Error

$	curl -X POST https://api.coactive.ai/api/v0/search/metadata-filters/text-to-transcript \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"dataset_id": "11973632-462e-4e14-a744-181b28ea931d",
>	"text_query": "climate change impact on agriculture"
>	}'