Audio / Text-to-Speech

Polly Neural

Text-to-speech model from Amazon AWS Bedrock · released Jul 2019

892Speech Arena Elo (±14)
#98-102rank range of 105
3,022blind votes
$16.00 / 1M charsAPI price
7 voicesvoices in the arena
Jul 2019release

95% confidence interval: Elo 878 – 906. 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
Jul 2019 (month precision)
Release source
Artificial Analysis Speech Arena (month precision)

More TTS models from Amazon AWS Bedrock