Antes de começar
Você forneceu ao Google um ID de projeto do Google Cloud para acessar o recurso de voz personalizada. Verifique se você ativou o faturamento e ativou as APIs Text-to-Speech e AutoML para esse projeto, além de instalar e inicializar o CLI do Google Cloud
Conceda o papel de AutoML Predictor à sua Conta do Google no seu projeto. Para mais instruções, consulte Conceder um único papel.
Como usar a linha de comando
Método HTTP e URL:
POST https://texttospeech.googleapis.com/v1beta1/text:synthesize
Corpo JSON da solicitação:
{
"input":{
"text":"Android is a mobile operating system developed by Google, based on the Linux kernel and designed primarily for touchscreen mobile devices such as smartphones and tablets."
},
"voice":{
"custom_voice":{
"reportedUsage":"REALTIME",
"model":"projects/{project_id}/locations/us-central1/models/{model_id}",
}
},
"audioConfig":{
"audioEncoding":"LINEAR16"
}
}
Salve o corpo da solicitação em um arquivo chamado request.json
e execute o comando a seguir, substituindo PROJECT_ID
pelo ID do projeto:
curl -X POST \ -H "Authorization: Bearer "$(gcloud auth print-access-token) \ -H "x-goog-user-project: PROJECT_ID" \ -H "Content-Type: application/json; charset=utf-8" \ -d @request.json \ https://texttospeech.googleapis.com/v1beta1/text:synthesize
Como usar a biblioteca de cliente do Python
Faça o download da biblioteca de cliente e execute o seguinte comando:
pip install texttospeech-custom-voice-beta-v1beta1-py.tar.gz
pip install protobuf --upgrade pip
Exemplo de código Python
"""Synthesize custom voice from the input string of text or ssml.
"""
from google.cloud import texttospeech_v1beta1
# Instantiate a client
client = texttospeech_v1beta1.TextToSpeechClient()
# Set the text input to be synthesized
synthesis_input = texttospeech_v1beta1.types.SynthesisInput(text="Hello, World!")
# Build the voice request, select the language code ("en-US") and specify
# custom voice model and speaker_id.
custom_voice = texttospeech_v1beta1.types.CustomVoiceParams(
reported_usage=texttospeech_v1beta1.enums.CustomVoiceParams.ReportedUsage.REALTIME,
model='projects/{project_id}/locations/us-central1/models/{model_id}')
voice = texttospeech_v1beta1.types.VoiceSelectionParams(
language_code='en-US',
custom_voice=custom_voice)
# Select the type of audio file you want returned
audio_config = texttospeech_v1beta1.types.AudioConfig(
audio_encoding=texttospeech_v1beta1.enums.AudioEncoding.LINEAR16)
# Perform the text-to-speech request on the text input with the selected
# voice parameters and audio file type
response = client.synthesize_speech(synthesis_input, voice, audio_config)
# The response's audio_content is binary.
with open('output.wav', 'wb') as out:
# Write the response to the output file.
out.write(response.audio_content)
print('Audio content written to file "output.wav"')