I am trying to get individual phoneme sounds from Google Text to Speech. I'm getting the individual phonetic spellings and corresponding IPA from dictionary.com.
For Ex) pizza (peet-suh) IPA: ('pit sə)
I'm using Python to get the response from the API and the ssml is,
<phoneme alphabet="ipa" ph="sə">suh</phoneme>
However, the audio comes out sounding 'sooh'.
The code for the request is as follows,
text='<phoneme alphabet="ipa" ph="sə">suh</phoneme>'
synthesis_input = texttospeech_v1beta1.SynthesisInput(ssml=text)
response = client.synthesize_speech(input = synthesis_input, voice = speaker, audio_config = config)
The client is also instantiated as
client = texttospeech_v1beta1.TextToSpeechClient()
It would be great if I could get some help with this.
