Hello,
we are interesting in a custom voice model which should be used for Dialogflow voicebot. As per this link https://cloud.google.com/text-to-speech/custom-voice/docs I am trying to submit a new model / request but was not able to finish it. Everything is prepared but when apply the curl command it ends with two different errors.
curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://texttospeech.googleapis.com/v1beta1/text:synthesiz
curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://texttospeech.googleapis.com/v1beta1/text:synthesize
{
"input":{
"text":"Android is a mobile operating system developed by Google, based on the Linux kernel and designed primarily for touchscreen mobile devices such as smartphones and tablets."
},
"voice":{
"languageCode":"en-US",
"custom_voice":{
"reportedUsage":"REALTIME",
"model":"projects/<xxx>/locations/us-central1/models/cctr",
}
},
"audioConfig":{
"audioEncoding":"LINEAR16"
}
}
First is missing language code where I add "languageCode":"en-US", based on the documentation but then it ends with missing model error. I think I missed some step but was not able to find which one, probably some step with model creation?
Any help will be appreciated.
Thank you,
Roman
LinkedIn
Twitter
