Aller au contenu

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

Listed

Speech Arena Elo 893 on Artificial Analysis, latency not measured; ranked 95th (tied) of 112 in the TTS for Voice Agents 2026 index.

Benchmark summary: 3.1/100, ranked 95th (tied) of 112 in the TTS for Voice Agents 2026 index (Listed). Strongest criterion: price, 2.5 of 5 points.

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

Visit website
Open weights Artificial Analysis StyleTTS Listed

Overall score

3.1 /100

95 th of 112

Score breakdown

  • Real-time speed 0 /60
  • Voice quality 0.6 /20
  • Accuracy 0 /15
  • Price 2.5 /5

Data checked on September 30, 2026

Updated after each benchmark capture

Every point comes from a public benchmark: sources · methodology

Gradium TTS Beta vs StyleTTS 2

StyleTTS 2 ranks 95th of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 3.1/100.

Real-time latency

Neither Coval nor Speko measures StyleTTS 2's latency, so it scores 0 of 60 on real-time speed and does not appear in the real-time ranking.

Accuracy (word error rate)

No accuracy measurement: Coval does not measure its word error rate and Speko does not rate its pronunciation robustness, so accuracy counts 0 of 15.

Voice quality

In the Artificial Analysis Speech Arena (capture of October 1, 2026), StyleTTS 2 has an Elo of 893 (±15, 95% confidence) from 2,440 blind comparisons, 86th highest of the 92 models Artificial Analysis rates.

Price

Artificial Analysis lists StyleTTS 2 at $2.8 per 1M characters (2nd lowest of the 78 models Artificial Analysis lists a price for).

Benchmark measurements

Artificial Analysis Speech Arena

Speech Arena Elo (blind listener preference)
893
Elo 95% interval (±)
15
Arena rank
86
Arena rank range
86-90
Arena appearances
2,440
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