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.

Request

This endpoint expects a multipart form containing a file.

filefileRequired

The file to align. All major audio and video formats are supported. The file size must be less than 1GB.

textstringRequired

The text to align with the audio or video. 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.

1	from elevenlabs import ElevenLabs
2
3	client = ElevenLabs(
4	api_key="YOUR_API_KEY",
5	)
6	client.forced_alignment.create(
7	text="text",
8	)

1	{
2	"characters": [
3	{
4	"text": "H",
5	"start": 0,
6	"end": 0.02
7	}
8	],
9	"words": [
10	{
11	"text": "Hello",
12	"start": 0,
13	"end": 1.02
14	}
15	]
16	}

Headers

Request

Response

Errors