Aller au contenu

MiniMax Speech 2.8 Turbo MiniMax · text-to-speech (TTS) API

Listed

Speech Arena Elo 1,152 on Artificial Analysis, latency not measured; ranked 46th (tied) of 112 in the TTS for Voice Agents 2026 index.

Benchmark summary: 9.3/100, ranked 46th (tied) of 112 in the TTS for Voice Agents 2026 index (Listed). Strongest criterion: voice quality, 8.4 of 20 points.

MiniMax Speech 2.8 Turbo is a proprietary text-to-speech (TTS) API from MiniMax, measured by two independent benchmarks: Artificial Analysis and Speko.

Overall score

9.3 /100

46 th of 112

Score breakdown

  • Real-time speed 0 /60
  • Voice quality 8.4 /20
  • Accuracy 0 /15
  • Price 0.9 /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 MiniMax Speech 2.8 Turbo

MiniMax Speech 2.8 Turbo ranks 46th of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 9.3/100.

Real-time latency

Neither Coval nor Speko measures MiniMax Speech 2.8 Turbo'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), MiniMax Speech 2.8 Turbo has an Elo of 1,152 (±11, 95% confidence) from 4,426 blind comparisons, 20th highest of the 92 models Artificial Analysis rates. Speko rates its naturalness at 1,385 Elo from blind A/B votes (39th highest of the 41 models Speko rates).

Price

Artificial Analysis lists MiniMax Speech 2.8 Turbo at $60 per 1M characters (62nd lowest of the 78 models Artificial Analysis lists a price for). Speko lists a cost of about $60 per 1M characters.

Scoring note

Artificial Analysis changed its Speech Arena Elo between the captures of September 30, 2026 and October 1, 2026 without a new measurement date (1,150, then 1,152): the score uses the average, 1,151. The value shown is the latest.

Languages tested

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

Benchmark measurements

Speko

Naturalness (Elo)
1,385
Price per 1M characters
60 USD
Measured on
2026-09-29
Speko model
speech-2.8-turbo
Speko model page
benchmarks.speko.ai

Artificial Analysis Speech Arena

Speech Arena Elo (blind listener preference)
1,152
Elo 95% interval (±)
11
Arena rank
20
Arena rank range
19-21
Arena appearances
4,426
Voices tested
8
Price per 1M characters
60 USD
Released
Feb 2026
Artificial Analysis model
Speech 2.8 Turbo
Artificial Analysis leaderboard
artificialanalysis.ai

Not collected

Similar TTS models