The WellSaid clips endpoint allows you to submit multiple clips in one request and so that they can be processed and returned asynchronously. Users can send up to 100 clips in a single request and then retrieve those clips after they are finished being processed by our text-to-speech models.

How do you use the endpoint?

Create Multiple Clips (Bulk)

Make a POST request to this URL, including your API key in the header:

https://api.wellsaidlabs.com/v1/tts/clips

An example curl command that has an array of clips to create:

curl --location 'https://api.wellsaidlabs.com/v1/tts/clips' \
--header 'X-API-KEY: <api-key-here>'
--header 'accept: */*' \
--header 'content-type: application/json' \
--data '
[
  {
  	"speaker_id": 7,
  	"text": "Make me my first clip"
	},
	{
  	"speaker_id": 8,
  	"text": "Now make me a second clip"
	},
  {
  	"speaker_id": 9,
  	"text": "Also make me this clip using a replacement library",
    "library_id": "YOUR_LIBRARY_ID"
	}
]
'

Response

Below is an example of a successful response showing one avatar with the following structure:

{
    "clip_ids": [
        "your_clip_id_1",
        "your_clip_id_2",
        "your_clip_id_3"
    ]
}

What are the endpoint limits?

100 Clips generated per request
Character limit of each "text"body is the same as the limit set by your plan
Can use any Avatar for each clip
Can use any Replacement Library for each clip

Details of response

Field	type	notes
text	string	The text you want synthesized into speech by Wellsaid
clip_id	string	The ID of the clip being generated by the text-to-speech models
speaker_id	integer	The Avatar you want to use for this request. See list here
status	string	Indicates the status of the clip and could read "PROCESSING", "FAILED", "COMPLETE"
url	string	The url where you can go to hear and download your clip once it has completed processing. The clip will remain available for one week.