Audio / Text-to-Speech

Chirp 3: HD

Text-to-speech model from Google DeepMind · released Mar 2025

1061Speech Arena Elo (±11)
#60-71rank range of 105
3,636blind votes
$30.00 / 1M charsAPI price
8 voicesvoices in the arena
Mar 2025release

95% confidence interval: Elo 1050 – 1072. 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
Mar 2025 (month precision)
Release source
Artificial Analysis Speech Arena (month precision)

More TTS models from Google DeepMind