synthesize_speech ¶

@contextmanager
def synthesize_speech(
    self,
    output_format: "capo_polly.types.output_format.OutputFormat",
    text: "capo_polly.types.text.Text",
    voice_id: "capo_polly.types.voice_id.VoiceId",
    *,
    config_overrides: Optional[PollyClientConfig] = None,
    engine: Optional["capo_polly.types.engine.Engine"] = None,
    language_code: Optional["capo_polly.types.language_code.LanguageCode"] = None,
    lexicon_names: Optional[
        "capo_polly.types.lexicon_name_list.LexiconNameList"
    ] = None,
    sample_rate: Optional["capo_polly.types.sample_rate.SampleRate"] = None,
    speech_mark_types: Optional[
        "capo_polly.types.speech_mark_type_list.SpeechMarkTypeList"
    ] = None,
    text_type: Optional["capo_polly.types.text_type.TextType"] = None,
) -> "Generator[capo_polly.types.synthesize_speech_output.SynthesizeSpeechOutput]":
    """<p>Synthesizes UTF-8 input, plain text or SSML, to a stream of bytes. SSML input must be valid, well-formed SSML. Some alphabets might not be available with all the voices (for example, Cyrillic might not be read at all by English voices) unless phoneme mapping is used. For more information, see <a href="https://docs.aws.amazon.com/polly/latest/dg/how-text-to-speech-works.html">How it Works</a>.</p>

    Args:
        engine: <p>Specifies the engine (<code>standard</code>, <code>neural</code>, <code>long-form</code>, or <code>generative</code>) for Amazon Polly to use when processing input text for speech synthesis. Provide an engine that is supported by the voice you select. If you don't provide an engine, the standard engine is selected by default. If a chosen voice isn't supported by the standard engine, this will result in an error. For information on Amazon Polly voices and which voices are available for each engine, see <a href="https://docs.aws.amazon.com/polly/latest/dg/voicelist.html">Available Voices</a>.</p>
        language_code: <p>Optional language code for the Synthesize Speech request. This is only necessary if using a bilingual voice, such as Aditi, which can be used for either Indian English (en-IN) or Hindi (hi-IN). </p> <p>If a bilingual voice is used and no language code is specified, Amazon Polly uses the default language of the bilingual voice. The default language for any voice is the one returned by the <a href="https://docs.aws.amazon.com/polly/latest/dg/API_DescribeVoices.html">DescribeVoices</a> operation for the <code>LanguageCode</code> parameter. For example, if no language code is specified, Aditi will use Indian English rather than Hindi.</p>
        lexicon_names: <p>List of one or more pronunciation lexicon names you want the service to apply during synthesis. Lexicons are applied only if the language of the lexicon is the same as the language of the voice. For information about storing lexicons, see <a href="https://docs.aws.amazon.com/polly/latest/dg/API_PutLexicon.html">PutLexicon</a>.</p>
        output_format: <p> The format in which the returned output will be encoded. For audio stream, this will be mp3, ogg_vorbis, ogg_opus, mu-law, a-law or pcm. For speech marks, this will be json. </p> <p>When pcm is used, the content returned is audio/pcm in a signed 16-bit, 1 channel (mono), little-endian format. </p>
        sample_rate: <p>The audio frequency specified in Hz.</p> <p>The valid values for mp3 and ogg_vorbis are "8000", "16000", "22050", "24000", "44100" and "48000". The default value for standard voices is "22050". The default value for neural voices is "24000". The default value for long-form voices is "24000". The default value for generative voices is "24000".</p> <p>Valid values for pcm are "8000" and "16000" The default value is "16000". </p> <p>Valid value for ogg_opus is "48000". </p> <p>Valid value for mu-law and a-law is "8000". </p>
        speech_mark_types: <p>The type of speech marks returned for the input text.</p>
        text: <p> Input text to synthesize. If you specify <code>ssml</code> as the <code>TextType</code>, follow the SSML format for the input text. </p>
        text_type: <p> Specifies whether the input text is plain text or SSML. The default value is plain text. For more information, see <a href="https://docs.aws.amazon.com/polly/latest/dg/ssml.html">Using SSML</a>.</p>
        voice_id: <p> Voice ID to use for the synthesis. You can get a list of available voice IDs by calling the <a href="https://docs.aws.amazon.com/polly/latest/dg/API_DescribeVoices.html">DescribeVoices</a> operation. </p>

    Raises:
        capo_polly.errors.engine_not_supported_exception.EngineNotSupportedException: <p>This engine is not compatible with the voice that you have designated. Choose a new voice that is compatible with the engine or change the engine and restart the operation.</p>
        capo_polly.errors.invalid_sample_rate_exception.InvalidSampleRateException: <p>The specified sample rate is not valid.</p>
        capo_polly.errors.invalid_ssml_exception.InvalidSsmlException: <p>The SSML you provided is invalid. Verify the SSML syntax, spelling of tags and values, and then try again.</p>
        capo_polly.errors.language_not_supported_exception.LanguageNotSupportedException: <p>The language specified is not currently supported by Amazon Polly in this capacity.</p>
        capo_polly.errors.lexicon_not_found_exception.LexiconNotFoundException: <p>Amazon Polly can't find the specified lexicon. This could be caused by a lexicon that is missing, its name is misspelled or specifying a lexicon that is in a different region.</p> <p>Verify that the lexicon exists, is in the region (see <a>ListLexicons</a>) and that you spelled its name is spelled correctly. Then try again.</p>
        capo_polly.errors.marks_not_supported_for_format_exception.MarksNotSupportedForFormatException: <p>Speech marks are not supported for the <code>OutputFormat</code> selected. Speech marks are only available for content in <code>json</code> format.</p>
        capo_polly.errors.service_failure_exception.ServiceFailureException: <p>An unknown condition has caused a service failure.</p>
        capo_polly.errors.ssml_marks_not_supported_for_text_type_exception.SsmlMarksNotSupportedForTextTypeException: <p>SSML speech marks are not supported for plain text-type input.</p>
        capo_polly.errors.text_length_exceeded_exception.TextLengthExceededException: <p>The value of the "Text" parameter is longer than the accepted limits. For the <code>SynthesizeSpeech</code> API, the limit for input text is a maximum of 6000 characters total, of which no more than 3000 can be billed characters. For the <code>StartSpeechSynthesisTask</code> API, the maximum is 200,000 characters, of which no more than 100,000 can be billed characters. SSML tags are not counted as billed characters.</p>
        capo_polly.errors.UnknownServiceError: The service returned an error code this client does not model.

    Examples:
        To synthesize speech
        Synthesizes plain text or SSML into a file of human-like speech.

        >>> client.synthesize_speech(lexicon_names=['example'], output_format='mp3', sample_rate='8000', text='All Gaul is divided into three parts', text_type='text', voice_id='Joanna')
    """

    def _handler(
        req: "OperationRequest[capo_polly.types.synthesize_speech_input.SynthesizeSpeechInput]",
    ) -> OperationResponse[
        "capo_polly.types.synthesize_speech_output.SynthesizeSpeechOutput"
    ]:
        import capo_polly._operations.parrot_v1.synthesize_speech

        output, http_response = (
            capo_polly._operations.parrot_v1.synthesize_speech.synthesize_speech(
                req.options, req.input
            )
        )
        return OperationResponse(output=output, response=http_response)

    def _redact_output(
        output: "capo_polly.types.synthesize_speech_output.SynthesizeSpeechOutput",
    ) -> dict[str, Any]:
        import capo_polly.types.synthesize_speech_output

        return capo_polly.types.synthesize_speech_output.redact_sensitive(output)

    interceptors_, options_ = self.operation_options(
        config_overrides,
        OperationLogging("SynthesizeSpeech", redact_output=_redact_output),
    )
    input_: capo_polly.types.synthesize_speech_input.SynthesizeSpeechInput = {
        "output_format": output_format,
        "text": text,
        "voice_id": voice_id,
    }
    if engine is not None:
        input_["engine"] = engine
    if language_code is not None:
        input_["language_code"] = language_code
    if lexicon_names is not None:
        input_["lexicon_names"] = lexicon_names
    if sample_rate is not None:
        input_["sample_rate"] = sample_rate
    if speech_mark_types is not None:
        input_["speech_mark_types"] = speech_mark_types
    if text_type is not None:
        input_["text_type"] = text_type

    response = execute_pipeline(
        OperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    try:
        yield response.output
    finally:
        response.response.close()