Aller au contenu

OpenVoice v2 OpenVoice · text-to-speech (TTS) API

Listed

Speech Arena Elo 952 on Artificial Analysis, latency not measured; ranked 88th of 112 in the TTS for Voice Agents 2026 index.

Benchmark summary: 3.8/100, ranked 88th of 112 in the TTS for Voice Agents 2026 index (Listed). Strongest criterion: price, 2.3 of 5 points.

OpenVoice v2 is an open-weights text-to-speech (TTS) API from OpenVoice, measured by one independent benchmark, Artificial Analysis.

Overall score

3.8 /100

88 th of 112

Score breakdown

  • Real-time speed 0 /60
  • Voice quality 1.5 /20
  • Accuracy 0 /15
  • Price 2.3 /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 OpenVoice v2 Compare with Maya 2 Global

OpenVoice v2 ranks 88th of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 3.8/100.

Real-time latency

Neither Coval nor Speko measures OpenVoice v2'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), OpenVoice v2 has an Elo of 952 (±13, 95% confidence) from 2,970 blind comparisons, 78th highest of the 92 models Artificial Analysis rates.

Price

Artificial Analysis lists OpenVoice v2 at $8.3 per 1M characters (8th lowest of the 78 models Artificial Analysis lists a price for).

Languages tested

Tested in Spanish, French, Japanese and Chinese by Artificial Analysis or Speko. A language missing here was not tested, which does not mean it is unsupported.

Benchmark measurements

Artificial Analysis Speech Arena

Speech Arena Elo (blind listener preference)
952
Elo 95% interval (±)
13
Arena rank
78
Arena rank range
77-79
Arena appearances
2,970
Voices tested
1
Price per 1M characters
8.3 USD
Released
Apr 2024
Artificial Analysis model
OpenVoice v2
Artificial Analysis leaderboard
artificialanalysis.ai

Not collected

Similar TTS models