Request Syntax URI Request Parameters Request Body Response Syntax Response Elements Errors See Also

SynthesizeSpeech

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.

Request Syntax


POST /v1/speech HTTP/1.1
Content-type: application/json

{
   "Engine": "string",
   "LanguageCode": "string",
   "LexiconNames": [ "string" ],
   "OutputFormat": "string",
   "SampleRate": "string",
   "SpeechMarkTypes": [ "string" ],
   "Text": "string",
   "TextType": "string",
   "VoiceId": "string"
}

URI Request Parameters

The request does not use any URI parameters.

Request Body

The request accepts the following data in JSON format.

Engine

Specifies the engine (standard, neural, long-form, or generative) 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 Available Voices.

Type: String

Valid Values: standard | neural | long-form | generative

Required: Yes

Type: String

Valid Values: standard | neural | long-form | generative

Required: No

LanguageCode

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 uses the default language of the bilingual voice. The default language for any voice is the one returned by the DescribeVoices operation for the LanguageCode parameter. For example, if no language code is specified, Aditi will use Indian English rather than Hindi.

Type: String

Required: No

LexiconNames

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.

Type: Array of strings

Array Members: Maximum number of 5 items.

Pattern: [0-9A-Za-z]{1,20}

Required: No

OutputFormat

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.

Type: String

Valid Values: json | mp3 | ogg_vorbis | pcm

Required: Yes

SampleRate

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". The default value for long-form voices is "24000". The default value for generative voices is "24000".

Valid values for pcm are "8000" and "16000" The default value is "16000".

Type: String

Required: No

SpeechMarkTypes

The type of speech marks returned for the input text.

Type: Array of strings

Array Members: Maximum number of 4 items.

Valid Values: sentence | ssml | viseme | word

Required: No

Text

Input text to synthesize. If you specify ssml as the TextType, follow the SSML format for the input text.

Type: String

Required: Yes

TextType

Specifies whether the input text is plain text or SSML. The default value is plain text. For more information, see Using SSML.

Type: String

Valid Values: ssml | text

Required: No

VoiceId

Voice ID to use for the synthesis. You can get a list of available voice IDs by calling the DescribeVoices operation.

Type: String

Required: Yes

Response Syntax


HTTP/1.1 200
Content-Type: ContentType
x-amzn-RequestCharacters: RequestCharacters

AudioStream

Response Elements

If the action is successful, the service sends back an HTTP 200 response.

The response returns the following HTTP headers.

ContentType

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 application/x-json-stream.

RequestCharacters

Number of characters synthesized.

The response returns the following as the HTTP body.

AudioStream: Stream containing the synthesized speech.

Errors

EngineNotSupportedException

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.

HTTP Status Code: 400

InvalidSampleRateException

The specified sample rate is not valid.

HTTP Status Code: 400

InvalidSsmlException

The SSML you provided is invalid. Verify the SSML syntax, spelling of tags and values, and then try again.

HTTP Status Code: 400

LanguageNotSupportedException

The language specified is not currently supported by Amazon Polly in this capacity.

HTTP Status Code: 400

LexiconNotFoundException

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.

Verify that the lexicon exists, is in the region (see ListLexicons) and that you spelled its name is spelled correctly. Then try again.

HTTP Status Code: 404

MarksNotSupportedForFormatException

Speech marks are not supported for the OutputFormat selected. Speech marks are only available for content in json format.

HTTP Status Code: 400

ServiceFailureException

An unknown condition has caused a service failure.

HTTP Status Code: 500

SsmlMarksNotSupportedForTextTypeException

SSML speech marks are not supported for plain text-type input.

HTTP Status Code: 400

TextLengthExceededException

The value of the "Text" parameter is longer than the accepted limits. For the SynthesizeSpeech 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 StartSpeechSynthesisTask 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.

HTTP Status Code: 400