Audio / Text-to-Speech

Eleven v4 Turbo

Text-to-speech model from ElevenLabs · released Sept 2026

1339Speech Arena Elo (±16)
#1-2rank range of 105
2,446blind votes
$40.00 / 1M charsAPI price
8 voicesvoices in the arena
Sept 2026release

95% confidence interval: Elo 1323 – 1355. 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
Sept 2026 (month precision)
Release source
Artificial Analysis Speech Arena (month precision)

More TTS models from ElevenLabs