Pattern-based speech synthesis using the API v3

import io
import pydub
import argparse

import yandex.cloud.ai.tts.v3.tts_pb2 as tts_pb2
import yandex.cloud.ai.tts.v3.tts_service_pb2_grpc as tts_service_pb2_grpc

def synthesize(iam_token, bytes_array) -> pydub.AudioSegment:
    template = "<template_phrase_with_markup>"
    # Template example: 'This is to remind you that your child has an appointment for {procedure} on {date} at {time}.'
    request = tts_pb2.UtteranceSynthesisRequest(
        output_audio_spec=tts_pb2.AudioFormatOptions(
            container_audio=tts_pb2.ContainerAudio(
                container_audio_type=tts_pb2.ContainerAudio.WAV
            )
        ),
        loudness_normalization_type=tts_pb2.UtteranceSynthesisRequest.LUFS,
        text_template = tts_pb2.TextTemplate(
            text_template = template,
            variables = [
                # List template variables.
                # The number of tts_pb2.TextVariable() list items depends on the number of template variables.
                tts_pb2.TextVariable(
                    variable_name = "<variable_name_in_template>",
                    # Example: '{time}'.
                    variable_value = "<text_for_synthesis>"
                    # Example: 'eight hours and thirty minutes'.
                )
            ]
        ),
        hints = [
            tts_pb2.Hints(
                audio_template = tts_pb2.AudioTemplate(
                    audio = tts_pb2.AudioContent(
                        # Upload a source audio for your template.
                        content = bytes_array,
                        audio_spec = tts_pb2.AudioFormatOptions(
                            container_audio = tts_pb2.ContainerAudio(
                                container_audio_type = tts_pb2.ContainerAudio.WAV
                            )
                        )
                    ),
                    text_template = tts_pb2.TextTemplate(
                        text_template = template,
                        variables = [
                            # List template variables.
                            # The number of tts_pb2.TextVariable() list items depends on the number of template variables.
                            tts_pb2.TextVariable(
                                variable_name = "<variable_name_in_template>",
                                variable_value = "<phrase_variable_part_text_in_template_audio_file>"
                            )
                        ]
                    ),
                    variables = [
                        # List the audio parameters of template variables.
                        # The number of tts_pb2.AudioVariable() list items depends on the number of template variables.
                        tts_pb2.AudioVariable(
                            variable_name = "<variable_name_in_template>",
                            # Length of the variable part of the phrase in the template audio (ms).
                            variable_length_ms = <variable_length>,
                            # Start of the variable part of the phrase in the template audio (ms).
                            variable_start_ms = <variable_start_time>
                        )
                    ]
                )
           ),
           tts_pb2.Hints(
               voice = "<your_voice_ID>"
           )
        ],
    )

    # Establish a connection with the server.
    cred = grpc.ssl_channel_credentials()
    channel = grpc.secure_channel('tts.api.cloud.yandex.net:443', cred)
    stub = tts_service_pb2_grpc.SynthesizerStub(channel)

    # Send data for synthesis.
    it = stub.UtteranceSynthesis(request, metadata=(
        ("authorization", f"Bearer {iam_token}"),
    ))

    # Process the server responses and write the output to a file.
    try:
        audio = io.BytesIO()
        for response in it:
            audio.write(response.audio_chunk.data)
        audio.seek(0)
        return pydub.AudioSegment.from_wav(audio)
    except grpc._channel._Rendezvous as err:
        print(f'Error code {err._state.code}, message: {err._state.details}')
        raise err


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--token', required=True, help='IAM token')
    parser.add_argument('--input', required=True, help='Template WAV file')
    parser.add_argument('--output', required=True, help='Output WAV file with synthesized speech')
    args = parser.parse_args()

    with open(args.input, 'rb') as file:
        speech = file.read()

    audio = synthesize(args.token, speech)
    with open(args.output, 'wb') as fp:
        audio.export(fp, format='wav')