Google 文字转语音 API 音调调整
Google text-to-speech API Pitch Adjustment
如何在这段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 documentation 对此不是很清楚。根据文档,'pitch' 可以在 [-20.0, 20.0] 范围内调整,但是这个参数可以在哪里调整。
audio_config = texttospeech.AudioConfig(pitch=-1.20, audio_encoding=texttospeech.AudioEncoding.LINEAR16)
如何在这段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 documentation 对此不是很清楚。根据文档,'pitch' 可以在 [-20.0, 20.0] 范围内调整,但是这个参数可以在哪里调整。
audio_config = texttospeech.AudioConfig(pitch=-1.20, audio_encoding=texttospeech.AudioEncoding.LINEAR16)