Generate speech from text

API that generates audio from text and accent. Generating audio through this endpoint costs 1 credit for every 30 seconds.

About Request Data Structure of Webhook

When using ‘text_to_speech’ API, if the ‘webhook_url’ is passed in the parameters, we will initiate a POST request to the webhook_url when the task succeeds or fails, with the following content:

{
    'id': 'string',
    'status': 'string',
    'failed_reason': 'string',
    'video_output': 'string',
}

Arguments:

• id (string): The unique identifier of the job
• status (string): The status of the job. Possible values are pending, in_queue, running, failed, done
• failed_reason (string): The reason of the failure if the job failed
• video_output (string): The URL of the video if the job is done

Note: We might send multiple requests for status changes.

Authorizations

X-API-ID

string

header

required

API ID, from your settings page.

X-API-KEY

string

header

required

API Key, from your settings page.

Body

script

string

required

Text to be converted to speech

Maximum length: 4000

accent

string | null

Accent to be used for the speech

webhook_url

string | null

Webhook URL for status updates. Default is null.

Maximum length: 200

Response

201 - application/json

id

string

required

script

string

required

Text to be converted to speech

Maximum length: 4000

output

string

required

Output audio url

media_job

string | null

required

is_hidden

boolean

required

Whether the job is hidden or not

status

string

required

failed_reason

string

required

Failed reason

created_at

string

required

updated_at

string

required

accent

string | null

Accent to be used for the speech

webhook_url

string | null

Webhook URL for status updates. Default is null.

Maximum length: 200