Aller au contenu

StyleTTS 2 StyleTTS · text-to-speech (TTS) API

Listener Elo 892 ±15 on Artificial Analysis (read October 22, 2026); latency not measured.

Benchmark summary: No speed tier: Coval, the source of the tiers, does not measure this model.

StyleTTS 2 is an open-weights text-to-speech (TTS) API from StyleTTS, measured by one independent benchmark, Artificial Analysis.

Speed tier

Not measured by Coval

No speed tier: Coval, the source of the tiers, does not measure this model.

Median time to first audioCoval, 30 days
—
P95 time to first audio (slow turns)Coval, 30 days
—
Naturalness EloSpeko
not rated
Listener Elo (95% interval)Artificial Analysis
892 ±15
Numbers and dates (0 to 1)Speko
not rated
List price per 1M charactersall sources
$2.8

Data read October 22, 2026. No combined score: methodology

Gradium TTS vs StyleTTS 2 Fastest TTS APIs, by speed tier

Speed

Neither Coval nor Speko measures StyleTTS 2's latency, so it has no speed tier and does not appear in the speed tiers.

Voice quality

In the Artificial Analysis Speech Arena it holds 892 ±15 Elo (95% interval), 94th highest of the 98 models Artificial Analysis rates; scores whose intervals overlap are a tie.

Numbers and dates

Speko has not scored its pronunciation of numbers and dates.

Price

Artificial Analysis lists $2.8. List prices, as each source prints them.

Benchmark measurements

Price (all sources)

Lowest list price per 1M characters
2.8 USD
Highest list price per 1M characters
2.8 USD

Artificial Analysis Speech Arena

Speech Arena Elo (blind listener preference)
892
Elo 95% interval (±)
15
Arena rank
94
Arena rank range
91-95
Arena appearances
2,590
Price per 1M characters
2.8 USD
Released
Jun 2023
Artificial Analysis model
StyleTTS 2
Artificial Analysis leaderboard
artificialanalysis.ai

Not collected

Similar TTS models