Bland Speech v3
Listed Proprietary · Bland AI
13.4
/100
Bland Speech v3 is a proprietary text-to-speech (TTS) API from Bland AI, measured by two independent benchmarks: Artificial Analysis and Speko.
Artificial Analysis Speko
Cartesia Sonic 3 Cartesia · text-to-speech (TTS) API
ListedSpeech Arena Elo 1,058 on Artificial Analysis, latency not measured; ranked 38th of 112 in the TTS for Voice Agents 2026 index.
Benchmark summary: 11.8/100, ranked 38th of 112 in the TTS for Voice Agents 2026 index (Listed). Strongest criterion: voice quality, 10.2 of 20 points.
Cartesia Sonic 3 is a proprietary text-to-speech (TTS) API from Cartesia, measured by two independent benchmarks: Artificial Analysis and Speko.
Proprietary Spanish German French Portuguese Japanese Chinese Arabic Hindi Vietnamese Artificial Analysis Speko Cartesia Listed
Overall score
11.8 /100
Score breakdown
- Real-time speed 0 /60
- Voice quality 10.2 /20
- Accuracy 0 /15
- Price 1.6 /5
Data checked on September 30, 2026
Updated after each benchmark capture
Every point comes from a public benchmark: sources · methodology
Cartesia Sonic 3 ranks 38th of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 11.8/100.
Real-time latency
Neither Coval nor Speko measures Cartesia Sonic 3'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), Cartesia Sonic 3 has an Elo of 1,058 (±12, 95% confidence) from 3,429 blind comparisons, 54th highest of the 92 models Artificial Analysis rates. Speko rates its naturalness at 1,551 Elo from blind A/B votes (17th highest of the 41 models Speko rates).
Price
Artificial Analysis lists Cartesia Sonic 3 at $49 per 1M characters (54th lowest of the 78 models Artificial Analysis lists a price for). Speko lists a cost of about $50 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 (1,059, then 1,058): the score uses the average, 1,058.5. 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)
- 1,551
- Price per 1M characters
- 50 USD
- Measured on
- 2026-09-08
- Speko model
- sonic-3
- Speko model page
- benchmarks.speko.ai
Artificial Analysis Speech Arena
- Speech Arena Elo (blind listener preference)
- 1,058
- Elo 95% interval (±)
- 12
- Arena rank
- 54
- Arena rank range
- 49-61
- Arena appearances
- 3,429
- Voices tested
- 8
- Price per 1M characters
- 49 USD
- Released
- Oct 2025
- Artificial Analysis model
- Sonic 3
- Artificial Analysis leaderboard
- artificialanalysis.ai
Not collected
- Speed (Coval time to first audio) — not measured by Coval (capture of 2026-10-01, 30-day window); counts 0
- Speed (Speko time to first audio) — listed by Speko without this value (capture of 2026-10-01); counts 0
- Accuracy (Coval word error rate) — not measured by Coval (capture of 2026-10-01, 30-day window); counts 0
- Accuracy (Speko robustness) — listed by Speko without this value (capture of 2026-10-01); counts 0
Similar TTS models
MiniMax Speech 2.8 HD
Listed Proprietary · MiniMax
11.4
/100
MiniMax Speech 2.8 HD is a proprietary text-to-speech (TTS) API from MiniMax, measured by two independent benchmarks: Artificial Analysis and Speko.
Spanish German French Portuguese
+13
Smallest.ai Lightning v3.1
Listed Proprietary · Smallest.ai
14
/100
Smallest.ai Lightning v3.1 is a proprietary text-to-speech (TTS) API from Smallest.ai, measured by two independent benchmarks: Artificial Analysis and Speko.
Spanish German French Hindi
+2