Start Enhancing

Initiates the audio enhancement process, including options for dereverberation, general enhancement, dewind, and dechimes. It also allows for transcription and sentiment analysis of the audio file spe

Headers

Key	Value
Content-Type	application/json
X-API-KEY	<Your API Key Here>

Request

POST

/api/v1/audiaize/unifiy/

Request Body

The request body should be a JSON object with the following structure:

Request Body

{
  "file_url": "string",
  "dereverb": boolean,
  "enhancement": boolean,
  "dewind": boolean,
  "dechimes": "boolean,
  "perform_transcription": boolean,
  "transcriptionLanguage":"string",
  "perform_sentimental_analysis": boolean,
  "perform_actionable": boolean,
  "perform_summary": boolean
}

Request Body(No enhacement)

Name	Type	Description
file_url*	string	URL of the audio file to be processed.
dereverb	boolean	Apply dereverberation if true.
dechimes	boolean	Remove chime noise if true.
dewind	boolean	Remove wind noise if true.
enhancement	boolean	Apply general audio quality enhancement if true.
perform_transcription	boolean	Transcribe audio to text if true.
perform_sentimental_analysis	boolean	Perform sentiment analysis on the transcribed text if true.
perform_actionable	boolean	Generate Actionable insights based on Transcription
transcriptionLanguage	string	Transcription Language of the audio by default en Options: - en - hi - hi-Latn
perform_summary	boolean	Generate Smmary based on Transcription

Good to know: Sentiment Analysis and Actionable Insights is based on the Transcription hence perform_transcription should be true for perform_sentimental_analysis and perform_actionable

Response

Response

{
  "id": {id},
  "file_url": "string",
  "perform_transcription": boolean,
  "perform_sentimental_analysis": boolean,
  "perform_actionable": boolean,
  "status": "started"
  "transcriptionLanguage": "string",
  "dereverb": boolean,
  "dewind": boolean,
  "dechimes": boolean,
  "enhancement": boolean"
}

Status Codes