Разберись:
# Build the voice request, select the language code ("en-US") and the ssml
# voice gender ("neutral")
voice = texttospeech.types.VoiceSelectionParams(
language_code='cs-CZ',
name="cs-CZ-Wavenet-A",
ssml_gender=texttospeech.enums.SsmlVoiceGender.FEMALE)
# Select the type of audio file you want returned
audio_config = texttospeech.types.AudioConfig(
audio_encoding=texttospeech.enums.AudioEncoding.MP3,
pitch=0)
# 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)
где параметр name можно найти в примере JSON над здесь . Например, на чешском языке это будет cs-CZ-Wavenet-A и "cs-CZ-Standard-A" .