Skip to main content
Voice format: aws.Polly.<Engine>.<VoiceId> Example: aws.Polly.Generative.Lucia The engine can also be parsed from a hyphenated suffix on the voice ID — e.g., Lucia-longform resolves to engine long-form.

​
Voice Samples

VoiceLanguageGenderSample
aws.Polly.Danielle-Neuralen-USFemale
aws.Polly.Gregory-Neuralen-USMale
aws.Polly.Lucia-Generativees-ESFemale

​
WebSocket

​
Query Parameters

ParameterTypeDefaultDescription
audio_formatstringmp3mp3, linear16, ogg_vorbis.
sample_rateinteger—8000, 16000, 22050, 24000.
languagestring—BCP-47 language code. Passed as language_code to Polly.
text_typestringtexttext or ssml. Polly supports SSML for fine-grained prosody control.

​
Voice Settings

FieldTypeDefaultDescription
enginestringstandardstandard, neural, generative, long-form.
output_formatstring—Any Polly output format.
sample_ratestring—e.g. "8000", "16000", "22050", "24000". Valid values depend on engine and format.
lexicon_namesarray—Pronunciation lexicon names to apply.
language_codestring—BCP-47. Overrides language query param.
text_typestringtexttext or ssml. Overrides query param.
{
  "text": " ",
  "voice_settings": {
    "engine": "generative",
    "output_format": "mp3",
    "sample_rate": "24000"
  }
}

​
REST API

​
Fields

FieldTypeDefaultDescription
enginestringstandardstandard, neural, generative, long-form.
output_formatstring—Polly output format.
sample_ratestring—Sample rate in Hz.
lexicon_namesarray—Pronunciation lexicon names.
language_codestring—BCP-47 language code.
text_typestringtexttext or ssml.
output_typestringbinary_outputbinary_output, base64_output, or audio_id.

​
Response

Default (binary_output): chunked audio bytes. Format depends on output_format. With output_type: "base64_output": JSON with base64-encoded audio. With output_type: "audio_id": JSON with an audio_url for deferred retrieval.