api_op_SynthesizeSpeech.go

// Code generated by private/model/cli/gen-api/main.go. DO NOT EDIT.

package polly

import (
	"context"
	"io"

	"github.com/aws/aws-sdk-go-v2/aws"
	"github.com/aws/aws-sdk-go-v2/internal/awsutil"
	"github.com/aws/aws-sdk-go-v2/private/protocol"
)

type SynthesizeSpeechInput struct {
	_ struct{} `type:"structure"`

	// Specifies the engine (standard or neural) for Amazon Polly to use when processing
	// input text for speech synthesis. Using a voice that is not supported for
	// the engine selected will result in an error.
	Engine Engine `type:"string" enum:"true"`

	// 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).
	//
	// If a bilingual voice is used and no language code is specified, Amazon Polly
	// will use the default language of the bilingual voice. The default language
	// for any voice is the one returned by the DescribeVoices (https://docs.aws.amazon.com/polly/latest/dg/API_DescribeVoices.html)
	// operation for the LanguageCode parameter. For example, if no language code
	// is specified, Aditi will use Indian English rather than Hindi.
	LanguageCode LanguageCode `type:"string" enum:"true"`

	// 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 PutLexicon (https://docs.aws.amazon.com/polly/latest/dg/API_PutLexicon.html).
	LexiconNames []string `type:"list"`

	// The format in which the returned output will be encoded. For audio stream,
	// this will be mp3, ogg_vorbis, or pcm. For speech marks, this will be json.
	//
	// When pcm is used, the content returned is audio/pcm in a signed 16-bit, 1
	// channel (mono), little-endian format.
	//
	// OutputFormat is a required field
	OutputFormat OutputFormat `type:"string" required:"true" enum:"true"`

	// The audio frequency specified in Hz.
	//
	// The valid values for mp3 and ogg_vorbis are "8000", "16000", "22050", and
	// "24000". The default value for standard voices is "22050". The default value
	// for neural voices is "24000".
	//
	// Valid values for pcm are "8000" and "16000" The default value is "16000".
	SampleRate *string `type:"string"`

	// The type of speech marks returned for the input text.
	SpeechMarkTypes []SpeechMarkType `type:"list"`

	// Input text to synthesize. If you specify ssml as the TextType, follow the
	// SSML format for the input text.
	//
	// Text is a required field
	Text *string `type:"string" required:"true"`

	// Specifies whether the input text is plain text or SSML. The default value
	// is plain text. For more information, see Using SSML (https://docs.aws.amazon.com/polly/latest/dg/ssml.html).
	TextType TextType `type:"string" enum:"true"`

	// Voice ID to use for the synthesis. You can get a list of available voice
	// IDs by calling the DescribeVoices (https://docs.aws.amazon.com/polly/latest/dg/API_DescribeVoices.html)
	// operation.
	//
	// VoiceId is a required field
	VoiceId VoiceId `type:"string" required:"true" enum:"true"`
}

// String returns the string representation
func (s SynthesizeSpeechInput) String() string {
	return awsutil.Prettify(s)
}

// Validate inspects the fields of the type to determine if they are valid.
func (s *SynthesizeSpeechInput) Validate() error {
	invalidParams := aws.ErrInvalidParams{Context: "SynthesizeSpeechInput"}
	if len(s.OutputFormat) == 0 {
		invalidParams.Add(aws.NewErrParamRequired("OutputFormat"))
	}

	if s.Text == nil {
		invalidParams.Add(aws.NewErrParamRequired("Text"))
	}
	if len(s.VoiceId) == 0 {
		invalidParams.Add(aws.NewErrParamRequired("VoiceId"))
	}

	if invalidParams.Len() > 0 {
		return invalidParams
	}
	return nil
}

// MarshalFields encodes the AWS API shape using the passed in protocol encoder.
func (s SynthesizeSpeechInput) MarshalFields(e protocol.FieldEncoder) error {
	e.SetValue(protocol.HeaderTarget, "Content-Type", protocol.StringValue("application/json"), protocol.Metadata{})

	if len(s.Engine) > 0 {
		v := s.Engine

		metadata := protocol.Metadata{}
		e.SetValue(protocol.BodyTarget, "Engine", protocol.QuotedValue{ValueMarshaler: v}, metadata)
	}
	if len(s.LanguageCode) > 0 {
		v := s.LanguageCode

		metadata := protocol.Metadata{}
		e.SetValue(protocol.BodyTarget, "LanguageCode", protocol.QuotedValue{ValueMarshaler: v}, metadata)
	}
	if s.LexiconNames != nil {
		v := s.LexiconNames

		metadata := protocol.Metadata{}
		ls0 := e.List(protocol.BodyTarget, "LexiconNames", metadata)
		ls0.Start()
		for _, v1 := range v {
			ls0.ListAddValue(protocol.QuotedValue{ValueMarshaler: protocol.StringValue(v1)})
		}
		ls0.End()

	}
	if len(s.OutputFormat) > 0 {
		v := s.OutputFormat

		metadata := protocol.Metadata{}
		e.SetValue(protocol.BodyTarget, "OutputFormat", protocol.QuotedValue{ValueMarshaler: v}, metadata)
	}
	if s.SampleRate != nil {
		v := *s.SampleRate

		metadata := protocol.Metadata{}
		e.SetValue(protocol.BodyTarget, "SampleRate", protocol.QuotedValue{ValueMarshaler: protocol.StringValue(v)}, metadata)
	}
	if s.SpeechMarkTypes != nil {
		v := s.SpeechMarkTypes

		metadata := protocol.Metadata{}
		ls0 := e.List(protocol.BodyTarget, "SpeechMarkTypes", metadata)
		ls0.Start()
		for _, v1 := range v {
			ls0.ListAddValue(protocol.QuotedValue{ValueMarshaler: protocol.StringValue(v1)})
		}
		ls0.End()

	}
	if s.Text != nil {
		v := *s.Text

		metadata := protocol.Metadata{}
		e.SetValue(protocol.BodyTarget, "Text", protocol.QuotedValue{ValueMarshaler: protocol.StringValue(v)}, metadata)
	}
	if len(s.TextType) > 0 {
		v := s.TextType

		metadata := protocol.Metadata{}
		e.SetValue(protocol.BodyTarget, "TextType", protocol.QuotedValue{ValueMarshaler: v}, metadata)
	}
	if len(s.VoiceId) > 0 {
		v := s.VoiceId

		metadata := protocol.Metadata{}
		e.SetValue(protocol.BodyTarget, "VoiceId", protocol.QuotedValue{ValueMarshaler: v}, metadata)
	}
	return nil
}

type SynthesizeSpeechOutput struct {
	_ struct{} `type:"structure" payload:"AudioStream"`

	// Stream containing the synthesized speech.
	AudioStream io.ReadCloser `type:"blob"`

	// Specifies the type audio stream. This should reflect the OutputFormat parameter
	// in your request.
	//
	//    * If you request mp3 as the OutputFormat, the ContentType returned is
	//    audio/mpeg.
	//
	//    * If you request ogg_vorbis as the OutputFormat, the ContentType returned
	//    is audio/ogg.
	//
	//    * If you request pcm as the OutputFormat, the ContentType returned is
	//    audio/pcm in a signed 16-bit, 1 channel (mono), little-endian format.
	//
	//    * If you request json as the OutputFormat, the ContentType returned is
	//    audio/json.
	ContentType *string `location:"header" locationName:"Content-Type" type:"string"`

	// Number of characters synthesized.
	RequestCharacters *int64 `location:"header" locationName:"x-amzn-RequestCharacters" type:"integer"`
}

// String returns the string representation
func (s SynthesizeSpeechOutput) String() string {
	return awsutil.Prettify(s)
}

// MarshalFields encodes the AWS API shape using the passed in protocol encoder.
func (s SynthesizeSpeechOutput) MarshalFields(e protocol.FieldEncoder) error {
	if s.ContentType != nil {
		v := *s.ContentType

		metadata := protocol.Metadata{}
		e.SetValue(protocol.HeaderTarget, "Content-Type", protocol.QuotedValue{ValueMarshaler: protocol.StringValue(v)}, metadata)
	}
	if s.RequestCharacters != nil {
		v := *s.RequestCharacters

		metadata := protocol.Metadata{}
		e.SetValue(protocol.HeaderTarget, "x-amzn-RequestCharacters", protocol.Int64Value(v), metadata)
	}
	// Skipping AudioStream Output type's body not valid.
	return nil
}

const opSynthesizeSpeech = "SynthesizeSpeech"

// SynthesizeSpeechRequest returns a request value for making API operation for
// Amazon Polly.
//
// 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 How it
// Works (https://docs.aws.amazon.com/polly/latest/dg/how-text-to-speech-works.html).
//
//    // Example sending a request using SynthesizeSpeechRequest.
//    req := client.SynthesizeSpeechRequest(params)
//    resp, err := req.Send(context.TODO())
//    if err == nil {
//        fmt.Println(resp)
//    }
//
// Please also see https://docs.aws.amazon.com/goto/WebAPI/polly-2016-06-10/SynthesizeSpeech
func (c *Client) SynthesizeSpeechRequest(input *SynthesizeSpeechInput) SynthesizeSpeechRequest {
	op := &aws.Operation{
		Name:       opSynthesizeSpeech,
		HTTPMethod: "POST",
		HTTPPath:   "/v1/speech",
	}

	if input == nil {
		input = &SynthesizeSpeechInput{}
	}

	req := c.newRequest(op, input, &SynthesizeSpeechOutput{})

	return SynthesizeSpeechRequest{Request: req, Input: input, Copy: c.SynthesizeSpeechRequest}
}

// SynthesizeSpeechRequest is the request type for the
// SynthesizeSpeech API operation.
type SynthesizeSpeechRequest struct {
	*aws.Request
	Input *SynthesizeSpeechInput
	Copy  func(*SynthesizeSpeechInput) SynthesizeSpeechRequest
}

// Send marshals and sends the SynthesizeSpeech API request.
func (r SynthesizeSpeechRequest) Send(ctx context.Context) (*SynthesizeSpeechResponse, error) {
	r.Request.SetContext(ctx)
	err := r.Request.Send()
	if err != nil {
		return nil, err
	}

	resp := &SynthesizeSpeechResponse{
		SynthesizeSpeechOutput: r.Request.Data.(*SynthesizeSpeechOutput),
		response:               &aws.Response{Request: r.Request},
	}

	return resp, nil
}

// SynthesizeSpeechResponse is the response type for the
// SynthesizeSpeech API operation.
type SynthesizeSpeechResponse struct {
	*SynthesizeSpeechOutput

	response *aws.Response
}

// SDKResponseMetdata returns the response metadata for the
// SynthesizeSpeech request.
func (r *SynthesizeSpeechResponse) SDKResponseMetdata() *aws.Response {
	return r.response
}