Analyzing Media Files

Overview

Hyperia can ingest any media file (audio or video) for analysis, transcription, computer vision analysis, and NLP enrichment. A variety of ingestion mechanisms are provided including direct file upload and Internet web crawling (public http/https URLs). In addition to audio transcription, many other enrichments are provided including dialog act labeling, sentiment analysis, topic extraction, intent and action extraction, summarization, shared screen analysis (slide extraction, title extraction, screen OCR and text extraction, etc).

Process Media File

Uploads a media file (audio or video) for processing and analysis by Hyperia's AI engine.

Endpoint:

~~/v1/workspace/id/<workspace_id>/ingest/file~~

HTTP Method:

~~PUT~~

URI Parameters:

Name	Parameter
workspace_id	ID of workspace to upload to

Multi-part PUT Payload:

Part	Description
payload	JSON part containing conversation metadata
file	File part containing the media file to process

JSON Metadata Part Format:

The "payload" part of the multi-part PUT payload should contain a JSON payload containing metadata on the conversation being processed (title, date, and time).

Name	Parameter
title	Title of the conversation
date	Date of the conversation (YYYY-MM-DD)
time	Time of the conversation (HH:MM:SS-ZZZZ)

Media File Part Format:

The "file" part of the multi-part PUT payload should contain the audio or video media file that should be processed. A valid content type should be passed with this part. Supported media formats may be seen here.

Returns:

If successful: ~~HTTP 200~~

Return Payload:

RESPONSE

{
    "guid": "GUID_OF_DOCUMENT"
}

Code Sample:

from hyperia import Hyperia
import sys

media_file_path = "/PATH/TO/SOME/MEDIA/FILE"

workspace_id = "SOME_WORKSPACE_ID"

recording_title = "SOME_RECORDING_TITLE"
recording_date = "SOME_RECORDING_DATE"
recording_time = "SOME_RECORDING_TIME"

hyperia = Hyperia()

response = hyperia.queue_media_file_ingestion(media_file_path, workspace_id, 
											  recording_title, recording_date,
											  recording_time)

if not response:
  	sys.exit(-1)

// success

Process Online Media

Downloads a HTTP or HTTPS media file (audio or video) from the Internet for processing and analysis by Hyperia's AI engine.