时间戳

首页 > 解决方案 > Google 文字转语音 API 音高调整

python-3.x - Google 文字转语音 API 音高调整

问题描述

如何在此代码中将音高调整为 -1.20：

from google.cloud import texttospeech

def text_to_wav(voice_name, text):
    language_code = "-".join(voice_name.split("-")[:2])
    text_input = texttospeech.SynthesisInput(text=text)
    voice_params = texttospeech.VoiceSelectionParams(
        language_code=language_code, name=voice_name)

    audio_config = texttospeech.AudioConfig(
        audio_encoding=texttospeech.AudioEncoding.LINEAR16)

    client = texttospeech.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'Audio content written to "{filename}"')

Google Text-to-Speech 文档对此并不十分清楚。根据文档，可以在 [-20.0, 20.0] 范围内调整“音高”，但是可以在哪里调整此参数。

标签： python-3.xtext-to-speechgoogle-text-to-speech

解决方案

audio_config = texttospeech.AudioConfig(pitch=-1.20, audio_encoding=texttospeech.AudioEncoding.LINEAR16)

推荐阅读