使用 AWS 的 Amazon Polly

Amazon Polly 是將文字轉換成逼真說話方式的服務，能夠讓您建立會說話的應用程式和打造全新的啟用語音產品類別

Create an AWS account 

到AWS 右上角「建立AWS帳戶」

Create a user with access to Polly 

AWS管理控制台 > AWS服務 > IAM

Add group 

存取管理 > 群組

1. 建立新群組
2. 連結政策 AmazonPollyFullAccess
   

Add user 

存取管理 > 使用者

1. 選擇 AWS 存取類型
   
2. Add user to group with Polly access
3. 記好access key and a secret access key

Configure Mac to access AWS 

1. 官網：安裝、更新和卸載 AWS CLI 第 2 版 於 macOS

   下載 macOS pkg 文件，並安裝

2. AWS Config

   aws configure
   

   AWS Access Key ID [None]: [Your_AWS Access Key ID]
   AWS Secret Access Key [None]: [Your_AWS Secret Access Key]
   Default region name [None]: ap-northeast-1
   Default output format [None]:
   

3. 安裝其他東西
   portaudio

   brew install portaudio
   

   boto3

   python3 -m pip install boto3
   

   pyaudio

   python3 -m pip install pyaudio
   

4. Python library

   vim polly.py
   

   import boto3
   import pygame
   import os
   import time
   import io
      
   class Polly():
    OUTPUT_FORMAT='mp3'
   
    def __init__(self, voiceId):
        self.polly = boto3.client('polly') #access amazon web service
        self.VOICE_ID = voiceId
   
    def say(self, textToSpeech): #get polly response and play directly
        pollyResponse = self.polly.synthesize_speech(Text=textToSpeech, OutputFormat=self.OUTPUT_FORMAT, VoiceId=self.VOICE_ID)
           
        pygame.mixer.init()
        pygame.init()  # this is needed for pygame.event.* and needs to be called after mixer.init() otherwise no sound is played 
           
        if os.name != 'nt':
            pygame.display.set_mode((1, 1)) #doesn't work on windows, required on linux
               
        with io.BytesIO() as f: # use a memory stream
            f.write(pollyResponse['AudioStream'].read()) #read audiostream from polly
            f.seek(0)
            pygame.mixer.music.load(f)
            pygame.mixer.music.set_endevent(pygame.USEREVENT)
            pygame.event.set_allowed(pygame.USEREVENT)
            pygame.mixer.music.play()
            pygame.event.wait() # play() is asynchronous. This wait forces the speaking to be finished before closing
               
        while pygame.mixer.music.get_busy() == True:
            pass
   
    def saveToFile(self, textToSpeech, fileName): #get polly response and save to file
        pollyResponse = self.polly.synthesize_speech(Text=textToSpeech, OutputFormat=self.OUTPUT_FORMAT, VoiceId=self.VOICE_ID)
           
        with open(fileName, 'wb') as f:
            f.write(pollyResponse['AudioStream'].read())
            f.close()
   

5. 編輯想要Polly說的話

   vim say.py
   

   from polly import Polly
      
   tts = Polly('Joanna')
   tts.say('Hi there, I\'m very glad you\'re reading my article. Leave a comment if you find it useful.')
   tts.saveToFile('Hi there, save the speech for later', 'joanna.mp3')
   

6. 執行say.py

   python3 say.py
   

   接著會產生你要的音檔joanna.mp3

src: https://catqbat.com/make-your-pi-speak-with-text-to-speech-fom-amazon-polly/

官方開發指南

Python Example