Skip to content
ArenaPlatform

Polly Neural

amazon/polly-neural

Polly's neural TTS engine (July 2019), a sequence-to-sequence model with a neural vocoder and the engine AWS still expands most: dozens of voices in 36 languages and variants, 19 regions, and a Newscaster style for four voices.

Get API KeyRead the Docs
API
curl "$AUDIOLAB_API_URL/v1/audio/speech" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "amazon/polly-neural",
  "input": "Make every word count.",
  "voice": "auto",
  "response_format": "mp3"
}' --output speech.mp3
Read docs
Input Price
$13.60 / 1M characters
Output Price
—
Input
Text
Output
Audio

Capabilities

Explore what Polly Neural supports, then use the API section for a request tailored to this model.

BatchStreamVoicesSsmlSpeech marks

Languages

Multilingual

Model Information

Product
Text-to-Speech
Release Date
Jul 30, 2019
Data Policy
No training
Region
US
Input
Text
Output
Audio
Provider Documentation

Playground

Try Polly Neural by Amazon Web Services. Requests use the selected workspace’s credits and API pricing.

Polly NeuralCredits —
Polly Neural
⌘ / Ctrl + Enter to send
Sign in to run a requestAPI reference

Providers

Compare available endpoints, pricing, and context limits for Polly Neural.

ProviderContextOutputInput PriceOutput PriceEndpoint
Amazon Web ServicesNot specifiedAudio$13.60 / 1M characters—
amazon/polly-neural:amazon

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max chars3000
Max total chars6000
Formatsmp3, ogg, opus, pcm, ulaw, alaw, json

Provider Notes

One-shot requests stream Polly's response body and support MP3, Ogg Opus, Ogg Vorbis, raw PCM, μ-law, A-law, SSML, lexicons, and JSON speech marks where the selected engine allows them. Speech marks replace audio and are unavailable on the generative engine. The generative model also supports AudioLab's bidirectional WebSocket in Polly's supported streaming regions. Long-form is limited to us-east-1; generative and neural availability are region-specific.

Performance

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

API
curl "$AUDIOLAB_API_URL/v1/audio/speech" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "amazon/polly-neural",
  "input": "Make every word count.",
  "voice": "auto",
  "response_format": "mp3"
}' --output speech.mp3
Read docs
Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

ParameterDetails
modelamazon/polly-neural — Required model identifier.
language_codeView Accepted Values
lexicon_namesView Accepted Values
sample_rateView Accepted Values
speech_mark_typesView Accepted Values
text_typeView Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max chars3000
Max total chars6000
Formatsmp3, ogg, opus, pcm, ulaw, alaw, json

Similar Models

Explore more text-to-speech and compare their capabilities.

ModelContextInput PriceOutput Price
Polly GenerativeAmazon Web ServicesNot specified$25.50 / 1M characters—
Polly Long-formAmazon Web ServicesNot specified$85.00 / 1M characters—
Polly StandardAmazon Web ServicesNot specified$3.40 / 1M characters—
Sonic 3.6CartesiaNot specified$38.25 / 1M characters—
Sonic 3.6 (2026-08-27)CartesiaNot specified$38.25 / 1M characters—
tts-rt-v2SonioxNot specified$11.985 / 1M characters—
View All Text-to-Speech