Audio / Text-to-Speech

Polly Long-Form

Text-to-speech model from Amazon AWS Bedrock · released Nov 2023

1026Speech Arena Elo (±13)
#78-86rank range of 105
2,106blind votes
$100.00 / 1M charsAPI price
3 voicesvoices in the arena
Nov 2023release

95% confidence interval: Elo 1013 – 1039. Models whose intervals overlap share a rank range.

How this is measured

Speech Arena (Text-to-Speech)

Elo rating (higher is better)

Models are ranked with an Elo system derived from blind user votes: listeners hear two speech samples generated from the same text and pick the one that sounds more natural. The provider-voice leaderboard uses each provider's own native voices. Each result is reported with a 95% interval and the number of votes (samples).

Release & sources

Release
Nov 2023 (month precision)
Release source
Artificial Analysis Speech Arena (month precision)

More TTS models from Amazon AWS Bedrock