google-cloud-texttospeech

import os from google.cloud import texttospeech_v1 as texttospeech def synthesize_text(text): """Synthesizes speech from the input string of text. Ensure GOOGLE_APPLICATION_CREDENTIALS environment variable is set or authenticate using `gcloud auth application-default login`. """ # Instantiates a client client = texttospeech.TextToSpeechClient() # Set the text input to be synthesized synthesis_input = texttospeech.SynthesisInput(text=text) # Build the voice request, select the language code ('en-US') and the SSML voice gender ('NEUTRAL') voice = texttospeech.VoiceSelectionParams( language_code="en-US", ssml_gender=texttospeech.SsmlVoiceGender.NEUTRAL, ) # Select the type of audio file you want returned audio_config = texttospeech.AudioConfig( audio_encoding=texttospeech.AudioEncoding.MP3 ) # Perform the text-to-speech request response = client.synthesize_speech( input=synthesis_input, voice=voice, audio_config=audio_config ) # The response's audio_content is binary. Write it to a file. output_filename = "output.mp3" with open(output_filename, "wb") as out: out.write(response.audio_content) print(f'Audio content written to file "{output_filename}"') if __name__ == "__main__": # For local development, set the GOOGLE_APPLICATION_CREDENTIALS environment variable. # For example: os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = '/path/to/your/key.json' # Or use `gcloud auth application-default login` if not os.environ.get('GOOGLE_APPLICATION_CREDENTIALS'): print("Warning: GOOGLE_APPLICATION_CREDENTIALS not set. Assuming gcloud ADC is configured.") text_to_synthesize = "Hello, world! This is a test of the Google Cloud Text-to-Speech API." synthesize_text(text_to_synthesize)