המרת טקסט לדיבור - מייקרוסופט אדג'

MicrosoftSpeech.md

עריכה - 9/5/21: הטוקן הפסיק לעבוד.
קובץ חדש כאן:
https://gist.github.com/MusiCode1/2db11a3e429e41e02bdf98febd239256
באמצעות הקוד הבא, ניתן להמיר טקסט לדיבור, ללא תשלום,
באמצעות הטוקן של מייקרוסופט אדג'.

https://gist.io/@MusiCode1/951019413c14bb8b9b0c91fd66359445

import requests
import time
from xml.etree import ElementTree
import os


def get_file(path):
    with open(path, 'r', encoding='utf-8') as f:
        r = f.read()
        return r


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.tts = get_file(os.getcwd() + '\\' + "test.txt")
        self.timestr = time.strftime("%Y%m%d-%H%M")
        self.access_token = None
        self.base_url = 'https://westus.tts.speech.microsoft.com/'

    def get_token(self):
        path = "sts/v1.0/issueToken"
        url = self.base_url + path
        headers = {
            'Ocp-Apim-Subscription-Key': self.subscription_key
        }
        response = requests.post(url, headers=headers)
        self.access_token = str(response.text)

    def save_audio(self):

        path = 'cognitiveservices/v1'
        url = self.base_url + path

        headers = {
            'Authorization': 'Bearer ' + self.access_token,
            'Content-Type': 'application/ssml+xml',
            # 'X-Microsoft-OutputFormat': 'riff-8khz-8bit-mono-mulaw',
            'X-Microsoft-OutputFormat': 'audio-24khz-160kbitrate-mono-mp3',
            'User-Agent': 'YOUR_RESOURCE_NAME'
        }

        # <speak xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="http://www.w3.org/2001/mstts" xmlns:emo="http://www.w3.org/2009/10/emotionml" version="1.0" xml:lang="en-US"><voice name="he-IL-HilaNeural"><prosody rate="0%" pitch="0%">You can replace this text with any text you wish. You can either write in this text box or paste your own text here.

        xml_body = ElementTree.Element('speak', version='1.0')
        xml_body.set('{http://www.w3.org/XML/1998/namespace}lang', 'he-IL')
        xml_body.set('xmlns', 'https://www.w3.org/2001/10/synthesis')

        parent = xml_body

        voice = ElementTree.SubElement(parent, 'voice')
        voice.set('{http://www.w3.org/XML/1998/namespace}lang', 'he-IL')
        voice.set('{http://www.w3.org/XML/1998/namespace}gender', 'Male')

        # name = 'HilaNeural'
        # name = 'Asaf'
        name = 'AvriNeural'

        voice.set(
            'name', 'Microsoft Server Speech Text to Speech Voice (he-IL, ' +
            name + ')'
        )
        # voice.text = self.tts

        parent = voice

        # prosody = ElementTree.SubElement(voice, 'prosody')
        # prosody.set('rate', '0')
        # prosody.set('pitch', 'x-high')
        #parent = prosody

        element1 = ElementTree.SubElement(parent, 'p')
        element1.text = self.tts

        body = ElementTree.tostring(xml_body)

        time_start = time.time()

        # response = requests.post(url, headers=headers, data=body, verify='C:\\netfree-ca-anywhere.crt')
        response = requests.post(url, headers=headers, data=body)

        print(time.time() - time_start)

        filename = 'sample-' + self.timestr + '.mp3'  # '.alaw'

        if response.status_code == 200:
            with open(filename, 'wb') as audio:
                audio.write(response.content)
                print("\nStatus code: " + str(response.status_code) +
                      "\nYour TTS is ready for playback.\n")

            os.startfile(os.getcwd() + '\\' + filename, 'open')
        else:
            print("\nStatus code: " + str(response.status_code) +
                  "\nSomething went wrong. Check your subscription key and headers.\n")
            print(response.content)


if __name__ == "__main__":
    subscription_key = "e6a6934efe57408fa2f3ce41c278b129"
    app = TextToSpeech(subscription_key)
    app.get_token()
    app.save_audio()