Create Forced Alignment

Force align an audio file to text. Use this endpoint to get the timing information for each character and word in an audio file based on a provided text transcript.

Headers

xi-api-keystringRequired

Request

This endpoint expects a multipart form containing a file.
filefileRequired
The file to align. All major audio formats are supported. The file size must be less than 1GB.
textstringRequired
The text to align with the audio. The input text can be in any format, however diarization is not supported at this time.

Response

Successful Response
characterslist of objects
List of characters with their timing information.
wordslist of objects
List of words with their timing information.
lossdouble

The average alignment loss/confidence score for the entire transcript, calculated from all characters.

Errors

422
Unprocessable Entity Error