POST
/
extract
curl --location 'https://api.mixpeek.com/extract' \
--header 'Authorization: Bearer API_KEY' \
--header 'Content-Type: application/json' \
--data '{
    "input": "s3://document.pdf",
    "modality": "text",
    "input_type": "url"
}'

The extract method allows you to pull data out of various modalities. Depending on the modality, different techniques can be applied:

  • image: optical character recognition, object detection, etc.
  • audio: transcription, diarization, etc.
  • video: object detection, scene detection, etc.
  • text: named entity recognition, tokenization, etc.

Request

input
string
required

The input URL, text, or base64 encoding of the object to extract.

modality
string
required

The type of data to be extracted (e.g., image, audio, video, text).

input_type
string
required

Specify whether the input is a url, base64, or text.