neural voices don't work pt-BR-FranciscaNeural

Question

I'm using an API for ENDPOINT: https://brazilsouth.api.cognitive.microsoft.com/sts/v1.0/issuetoken and I trying to implement a tutorial present in this site: https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/rest-text-to-speech but I don't able to make it work. When I get a listVoices don't show a pt-BR-FranciscaNeural but in the docs it says that the voice is available.

import requests
import time
from xml.etree import ElementTree

try:
    input = input
except NameError:
    pass

class TextToSpeech(object):
    def __init__(self, subscription_key):
        self.subscription_key = subscription_key
        self.tts = input("What would you like to convert to speech: ")
        self.timestr = time.strftime("%Y%m%d-%H%M")
        self.access_token = None
        
    def get_token(self):
        fetch_token_url = "https://brazilsouth.api.cognitive.microsoft.com/sts/v1.0/issueToken"
        headers = {
            'Ocp-Apim-Subscription-Key': self.subscription_key
        }
        response = requests.post(fetch_token_url, headers=headers)
        self.access_token = str(response.text)
    
    def save_audio(self):
        base_url = 'https://brazilsouth.tts.speech.microsoft.com/'
        path = 'cognitiveservices/v1'
        constructed_url = base_url + path
        headers = {
            'Authorization': 'Bearer ' + self.access_token,
            'Content-Type': 'application/ssml+xml',
            'X-Microsoft-OutputFormat': 'riff-24khz-16bit-mono-pcm',
            'User-Agent': 'YOUR_RESOURCE_NAME'
        }
        xml_body = ElementTree.Element('speak', version='1.0')
        xml_body.set('{http://www.w3.org/XML/1998/namespace}lang', 'pt-br')
        voice = ElementTree.SubElement(xml_body, 'voice')
        voice.set('{http://www.w3.org/XML/1998/namespace}lang', 'pt-BR')
        voice.set(
            'name', 'Microsoft Server Speech Text to Speech Voice (pt-BR, FranciscaNeural)')
        voice.text = self.tts
        
        body = ElementTree.tostring(xml_body)

        response = requests.post(constructed_url, headers=headers, data=body)
        if response.status_code == 200:
            with open('sample-' + self.timestr + '.wav', 'wb') as audio:
                audio.write(response.content)
                print("\nStatus code: " + str(response.status_code) +
                    "\nYour TTS is ready for playback.\n")
        else:
            print("\nStatus code: " + str(response.status_code) +
                "\nSomething went wrong. Check your subscription key and headers.\n")

if __name__ == "__main__":
    subscription_key = "put-here-a-keycode"
    app = TextToSpeech(subscription_key)
    app.get_token()
    app.save_audio()

Answer 1

I solved the problem, I changed the location of the server, because I found that what I used did not meet the neural language.

I managed to use Francisca's voice using another server:

fetch_token_url="https://eastus.api.cognitive.microsoft.com/sts/v1.0/issueToken"

it's working perfectly

Answer 2

Pls refer to this thread: https://github.com/MicrosoftDocs/azure-docs/issues/52032

As per thread, there is a known issue that is being worked actively and pt-BR-FranciscaNeural has been removed intentionally until fix.