en-US-JennyNeural.larry or a URL), please refer to the Generate Audio From Text endpoint page./v1/convert endpoint must contain the SSML to be converted to speech, along with the voice to be used for the conversion.ssml field in the request body. It is an array of SSML strings. An SSML string looks like: <speak><p>Hello my friend <break time="0.5s"/></p></speak>.transcriptionId in the response to check the conversion status in the Get Article Conversion Status endpoint endpoint.curl --location 'https://dev.your-api-server.com/api/v1/convert/' \
--header 'content-type: application/json' \
--data '{
"ssml": [
"<speak><p>Hello my friend. <break time=\"0.5s\"/> Hmm...</p></speak>"
],
"voice": "en-US-JennyNeural"
}'{
"status": "CREATED",
"transcriptionId": "-NOjGbpFU1Exf3DxhLHU",
"contentLength": 1,
"wordCount": 4
}