GCP ; API GCPのText to Speech API を利用しナレーションを作成する

GCPのText to Speech API を利用しナレーションを作成する

import google.cloud.texttospeech as tts


def text_to_wav(voice_name: str, text: str):
    language_code = "-".join(voice_name.split("-")[:2])
    text_input = tts.SynthesisInput(text=text)
    voice_params = tts.VoiceSelectionParams(
        language_code=language_code, name=voice_name
    )
    audio_config = tts.AudioConfig(audio_encoding=tts.AudioEncoding.LINEAR16)

    client = tts.TextToSpeechClient()
    response = client.synthesize_speech(
        input=text_input, voice=voice_params, audio_config=audio_config
    )

    filename = f"{language_code}.wav"
    with open(filename, "wb") as out:
        out.write(response.audio_content)
        print(f'Generated speech saved to "{filename}"')

実際ナレーションを作ったCodeは、

t2s.py

Created on Sun Jan  3 07:34:38 2021

@author: sf9
"""

from datetime import datetime
from pytz import timezone
from google.cloud import texttospeech
from google.oauth2 import service_account

credentials = service_account.Credentials.from_service_account_file('credentials.json')
client = texttospeech.TextToSpeechClient(credentials=credentials)

f = open('t2s.txt', 'r')
tdata = f.read()
f.close()

synthesis_input = texttospeech.types.SynthesisInput(
 text=tdata)

voice = texttospeech.types.VoiceSelectionParams(
  language_code='ja-JP',
  name='ja-JP-Wavenet-D',
  ssml_gender=texttospeech.enums.SsmlVoiceGender.NEUTRAL)

audio_config = texttospeech.types.AudioConfig(
  audio_encoding=texttospeech.enums.AudioEncoding.MP3,
  speaking_rate = 1.3, pitch = -2.0
  )

response = client.synthesize_speech(synthesis_input, voice, audio_config)

now = datetime.now(timezone('Asia/Tokyo'))
filename = now.strftime('%Y-%m-%d_%H%M%S.mp3')
with open(filename, 'wb') as out:
  out.write(response.audio_content)
  print(f'Audio content written to file {filename}')

プレゼン用に作成した男性のナレーション

t2s.txt
を作成し読み込ませるとタイムスタンプがファイル名のmp3が生成される