Aller au contenu

Bland Speech v3 Bland AI · text-to-speech (TTS) API

Listed

303 ms P50 time-to-first-audio on Speko; ranked 37th of 112 in the TTS for Voice Agents 2026 index.

Benchmark summary: 13.4/100, ranked 37th of 112 in the TTS for Voice Agents 2026 index (Listed). Strongest criterion: voice quality, 9.7 of 20 points.

Bland Speech v3 is a proprietary text-to-speech (TTS) API from Bland AI, measured by two independent benchmarks: Artificial Analysis and Speko.

Overall score

13.4 /100

37 th of 112

Score breakdown

  • Real-time speed 0.9 /60
  • Voice quality 9.7 /20
  • Accuracy 0.6 /15
  • Price 2.2 /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 Bland Speech v3 Compare with Cartesia Sonic 3

Bland Speech v3 ranks 37th of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 13.4/100.

Real-time latency

Speko measures a P50 TTFA of 303 ms from US East (n=30), dated August 20, 2026: 20th lowest of the 29 models Speko measures.

Accuracy (word error rate)

Speko rates its pronunciation robustness on numbers, dates and currency at 0.22 on a 0-to-1 scale (19th highest of the 28 models Speko rates).

Voice quality

In the Artificial Analysis Speech Arena (capture of October 1, 2026), Bland Speech v3 has an Elo of 1,035 (±13, 95% confidence) from 2,296 blind comparisons, 64th highest of the 92 models Artificial Analysis rates. Speko rates its naturalness at 1,569 Elo from blind A/B votes (14th highest of the 41 models Speko rates).

Price

Artificial Analysis lists Bland Speech v3 at $40 per 1M characters (49th lowest of the 78 models Artificial Analysis lists a price for). Speko lists a cost of about $40 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 (1,036, then 1,035): the score uses the average, 1,035.5. The value shown is the latest. Speko changed its pronunciation robustness between the captures of September 30, 2026 and October 1, 2026 without a new measurement date (0, then 0.22): the score uses the average, 0.11. The value shown is the latest.

Benchmark measurements

Speko

P50 TTFA, US East
303 ms
Naturalness (Elo)
1,569
Pronunciation robustness (0 to 1)
0.22
Voice drift (lower is steadier)
12
Price per 1M characters
40 USD
Measured on
2026-08-20
Speko model
bland-speech
Speko model page
benchmarks.speko.ai

Artificial Analysis Speech Arena

Speech Arena Elo (blind listener preference)
1,035
Elo 95% interval (±)
13
Arena rank
64
Arena rank range
59-71
Arena appearances
2,296
Voices tested
8
Price per 1M characters
40 USD
Released
Aug 2026
Artificial Analysis model
Bland Speech v3
Artificial Analysis leaderboard
artificialanalysis.ai

Not collected

Similar TTS models