Amazon Polly

Listeners rate Cartesia's Sonic 3.6 above every Amazon Polly engine.

ServiceNow, Decagon, and Quora run their production voice agents on Cartesia. One model, 44 languages, first audio in under 90ms.

2X Solutions logo
arini logo
toby logo

Voice quality

Listeners rate Sonic 3.6 above every Polly engine

  • Artificial Analysis plays listeners two clips of the same line without naming the model, and rates every model on the board the same way.
  • Sonic 3.6 leads Polly Generative, Polly's highest-rated engine, by more than 200 points.

Provider Voice Arena Elo

Higher is better

Artificial AnalysisOctober 2026
1291
1065
1030
896
830
Sonic 3.6
Cartesia
Amazon Polly
Polly Generative
Amazon Polly
Amazon Polly
Polly Long-form
Amazon Polly
Amazon Polly
Polly Neural
Amazon Polly
Amazon Polly
Polly Standard
Amazon Polly

Speed

Sonic 3.6 generates faster than Polly's two highest-rated engines

  • Artificial Analysis times every model on the board with the same harness, in characters generated per second.
  • Sonic 3.6 outpaces Polly Generative and Polly Long-form, so the voice listeners prefer is also the quicker one.

Characters per second

Higher is better

Artificial AnalysisOctober 2026
155.9
85.5
67.3
Sonic 3.6
Cartesia
Amazon Polly
Polly Generative
Amazon Polly
Amazon Polly
Polly Long-form
Amazon Polly

Reasons why companies choose Cartesia over Amazon Polly

CartesiaAmazon Polly
  1. Human-like naturalness

    Artificial Analysis
    Cartesia
    1291 Elo
    Amazon Polly
    1065 EloPolly Generative1030 EloPolly Long-form896 EloPolly Neural830 EloPolly Standard

    October 2026

  2. Languages

    Cartesia
    44 languages from one model, with native accents
    Amazon Polly
    Generative voices in 9 languages
  3. Custom voices

    Cartesia
    Instant clone from 10 seconds, professional clone from 30 minutes, on the public API
    Amazon Polly
    Brand Voice, a custom engagement with the Amazon Polly team
  4. Deployment

    Cartesia
    On-prem and air-gapped, already running at government, healthcare, and financial institutions, behind a 99.9% uptime SLA
    Amazon Polly
    Generative voices in 10 AWS regions
  5. End-to-end stack

    Cartesia
    TTS, STT, and Agents from one vendor, on one API
    Amazon Polly
    Polly for speech, with transcription and agents in separate AWS services

Frequently asked questions

Is AWS Polly the same as Amazon Polly?

Yes. Amazon Polly is the text to speech service in AWS, and it is searched under both names. This page compares Sonic 3.6 with all four Polly engines: Generative, Long-form, Neural, and Standard.

How is the quality score measured?

It comes from Artificial Analysis, an independent benchmark. Listeners hear two clips of the same line without being told which model produced either, and pick the one they prefer. Sonic 3.6 rates above all four Polly engines: Generative, Long-form, Neural, and Standard.

How many languages does Cartesia support?

44 languages from one model, including English, Spanish, French, German, and Japanese. Accents are calibrated per region rather than bolted onto an English model. Polly's generative voices cover 9 languages.

Can I use my own voice with Cartesia?

Yes. An instant clone takes 10 seconds of audio and a professional clone takes 30 minutes. Both are self-serve on the public API. Amazon Polly's custom voice, Brand Voice, is built with the Polly team as a custom engagement.

Can I run Cartesia on my own infrastructure?

Yes. Cartesia deploys on-prem and air-gapped, which teams in healthcare, finance, and government use to keep audio inside their own network, backed by a 99.9% uptime SLA.

How long does it take to switch from Amazon Polly?

One to two weeks for most teams. Cartesia is integrated into the major voice agent platforms and every model is on the public API, so there is no platform to move onto and nothing to unpick later.

Get started today

Talk to an expert.

Connect with a member of our team and learn how Cartesia can help you build world-class voice experiences.

Contact Sales

Start building.

Access our models via API and bring a voice agent into production in minutes.

Try Cartesia