StartSpeechSynthesisTask与 Amazon SDK 或 CLI 配合使用

合成文本

以下start-speech-synthesis-task示例合成了中的文本，text_file.txt并将生成的 MP3 文件存储在指定的存储桶中。

aws polly start-speech-synthesis-task \
    --output-format mp3 \
    --output-s3-bucket-name amzn-s3-demo-bucket \
    --text  file://text_file.txt \
    --voice-id Joanna

输出：

{
    "SynthesisTask": {
        "TaskId": "70b61c0f-57ce-4715-a247-cae8729dcce9",
        "TaskStatus": "scheduled",
        "OutputUri": "https://s3.us-east-2.amazonaws.com/amzn-s3-demo-bucket/70b61c0f-57ce-4715-a247-cae8729dcce9.mp3",
        "CreationTime": 1603911042.689,
        "RequestCharacters": 1311,
        "OutputFormat": "mp3",
        "TextType": "text",
        "VoiceId": "Joanna"
    }
}

有关更多信息，请参阅《Amazon Polly 开发人员指南》中的创建长音频文件。

class PollyWrapper:
    """Encapsulates Amazon Polly functions."""

    def __init__(self, polly_client, s3_resource):
        """
        :param polly_client: A Boto3 Amazon Polly client.
        :param s3_resource: A Boto3 Amazon Simple Storage Service (Amazon S3) resource.
        """
        self.polly_client = polly_client
        self.s3_resource = s3_resource
        self.voice_metadata = None


    def do_synthesis_task(
        self,
        text,
        engine,
        voice,
        audio_format,
        s3_bucket,
        lang_code=None,
        include_visemes=False,
        wait_callback=None,
    ):
        """
        Start an asynchronous task to synthesize speech or speech marks, wait for
        the task to complete, retrieve the output from Amazon S3, and return the
        data.

        An asynchronous task is required when the text is too long for near-real time
        synthesis.

        :param text: The text to synthesize.
        :param engine: The kind of engine used. Can be standard or neural.
        :param voice: The ID of the voice to use.
        :param audio_format: The audio format to return for synthesized speech. When
                             speech marks are synthesized, the output format is JSON.
        :param s3_bucket: The name of an existing Amazon S3 bucket that you have
                          write access to. Synthesis output is written to this bucket.
        :param lang_code: The language code of the voice to use. This has an effect
                          only when a bilingual voice is selected.
        :param include_visemes: When True, a second request is made to Amazon Polly
                                to synthesize a list of visemes, using the specified
                                text and voice. A viseme represents the visual position
                                of the face and mouth when saying part of a word.
        :param wait_callback: A callback function that is called periodically during
                              task processing, to give the caller an opportunity to
                              take action, such as to display status.
        :return: The audio stream that contains the synthesized speech and a list
                 of visemes that are associated with the speech audio.
        """
        try:
            kwargs = {
                "Engine": engine,
                "OutputFormat": audio_format,
                "OutputS3BucketName": s3_bucket,
                "Text": text,
                "VoiceId": voice,
            }
            if lang_code is not None:
                kwargs["LanguageCode"] = lang_code
            response = self.polly_client.start_speech_synthesis_task(**kwargs)
            speech_task = response["SynthesisTask"]
            logger.info("Started speech synthesis task %s.", speech_task["TaskId"])

            viseme_task = None
            if include_visemes:
                kwargs["OutputFormat"] = "json"
                kwargs["SpeechMarkTypes"] = ["viseme"]
                response = self.polly_client.start_speech_synthesis_task(**kwargs)
                viseme_task = response["SynthesisTask"]
                logger.info("Started viseme synthesis task %s.", viseme_task["TaskId"])
        except ClientError:
            logger.exception("Couldn't start synthesis task.")
            raise
        else:
            bucket = self.s3_resource.Bucket(s3_bucket)
            audio_stream = self._wait_for_task(
                10, speech_task["TaskId"], "speech", wait_callback, bucket
            )

            visemes = None
            if include_visemes:
                viseme_data = self._wait_for_task(
                    10, viseme_task["TaskId"], "viseme", wait_callback, bucket
                )
                visemes = [
                    json.loads(v) for v in viseme_data.read().decode().split() if v
                ]

            return audio_stream, visemes

    TRY.
        " Only pass optional parameters if they have values
        IF iv_lang_code IS NOT INITIAL AND iv_s3_key_prefix IS NOT INITIAL.
          oo_result = lo_ply->startspeechsynthesistask(
            iv_engine = iv_engine
            iv_outputformat = iv_audio_format
            iv_outputs3bucketname = iv_s3_bucket
            iv_outputs3keyprefix = iv_s3_key_prefix
            iv_text = iv_text
            iv_voiceid = iv_voice_id
            iv_languagecode = iv_lang_code ).
        ELSEIF iv_lang_code IS NOT INITIAL.
          oo_result = lo_ply->startspeechsynthesistask(
            iv_engine = iv_engine
            iv_outputformat = iv_audio_format
            iv_outputs3bucketname = iv_s3_bucket
            iv_text = iv_text
            iv_voiceid = iv_voice_id
            iv_languagecode = iv_lang_code ).
        ELSEIF iv_s3_key_prefix IS NOT INITIAL.
          oo_result = lo_ply->startspeechsynthesistask(
            iv_engine = iv_engine
            iv_outputformat = iv_audio_format
            iv_outputs3bucketname = iv_s3_bucket
            iv_outputs3keyprefix = iv_s3_key_prefix
            iv_text = iv_text
            iv_voiceid = iv_voice_id ).
        ELSE.
          oo_result = lo_ply->startspeechsynthesistask(
            iv_engine = iv_engine
            iv_outputformat = iv_audio_format
            iv_outputs3bucketname = iv_s3_bucket
            iv_text = iv_text
            iv_voiceid = iv_voice_id ).
        ENDIF.
        MESSAGE 'Speech synthesis task started.' TYPE 'I'.
      CATCH /aws1/cx_plyinvalids3bucketex.
        MESSAGE 'Invalid S3 bucket.' TYPE 'E'.
      CATCH /aws1/cx_plyinvalidssmlex.
        MESSAGE 'Invalid SSML.' TYPE 'E'.
      CATCH /aws1/cx_plylexiconnotfoundex.
        MESSAGE 'Lexicon not found.' TYPE 'E'.
      CATCH /aws1/cx_plyservicefailureex.
        MESSAGE 'Service failure occurred.' TYPE 'E'.
      CATCH /aws1/cx_plytextlengthexcdex.
        MESSAGE 'Text length exceeded maximum.' TYPE 'E'.
    ENDTRY.