whatmodel.sh / tts / Amazon Polly Neural

Amazon Polly Neural

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Amazon Polly Neural is a closed-weights text-to-speech model from Amazon Web Services.

Catalogue identity notes

Source product model polly-neural; voice Zhiyu. June 2026 invocation. Do not map Azure Neural to Azure HD or Polly Neural to Polly Generative.

44.6±4.4#79 of 118 text-to-speech modelsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

Score within the Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot comparison set only.

$ how it compares

The text-to-speech models ranked either side of Amazon Polly Neural, out of 148 with a score.

#modelscorewhereRAMreleased
98Qwen3-TTS 12Hz 0.6B CustomVoice Alibaba (Qwen)46±6comparison only2026-01
99Dia2 2B Nari Labs45±6local~8.1GB2025-11
100Amazon Polly Neural Amazon Web Services45±4api $16.00/M chars
101KittenTTS Nano 0.8 KittenML44±5comparison only2026-02
102GPT-SoVITS v2 RVC-Boss44±4local~1.1GB2024-08

see all text-to-speech models · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 92% of its score
testresultvs the others in its rundifficultycountswhy
CN-NewsTTS v0.1 · strict pronunciation accuracy24.4% ✎█··▄·█··▄··▄ beats 0/6hard · avg 32%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 92%typical

$ where to run it

Through an API

api · $16.00/M chars · aws.amazon.com ↗ · price sourceUSD per 1M characters: Amazon Polly Neural voices are priced at $16.00 per 1 million characters (outside the free tier). Product: Amazon Polly. API model: engine=neural. Settings: standard AWS regions. Price basis: published list rate. Exclusions: free tier, GovCloud ($19.20). Currency: USD. AWS official pricing page, observed 2026-09-25.

$ how the score was worked out · CN-NewsTTS Bench v0.1 92%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
CN-NewsTTS Bench v0.11▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 92%CC BY 4.0
prior · pull toward the middle▇▇ 8%
weighted average= 44.6

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json