TTS API comparison 2026
Gradium TTS Beta vs Cartesia Sonic 3.5 Gradium vs Cartesia · text-to-speech for voice agents
Gradium TTS Beta ranks 1st of 112 with 76.8/100; Cartesia Sonic 3.5 ranks 8th with 58.5/100: a gap of 18.3 points on the same public rules, built on Coval, Speko and Artificial Analysis.
Data checked on September 30, 2026 · Coval 30-day window ending October 1, 2026 · updated after each benchmark capture
Side-by-side benchmark
| Measure | Gradium TTS Beta | Cartesia Sonic 3.5 |
|---|---|---|
| Overall score | 76.8/100 | 58.5/100 |
| Rank | 1st of 112 | 8th of 112 |
| Real-time speed /60 | 58.7 | 37.1 |
| Voice quality /20 | 7.8 | 15.8 |
| Accuracy /15 | 9.8 | 4 |
| Price /5 | 0.5 | 1.6 |
| P50 / median time-to-first-audio Coval, 30-day window | 47.2 ms | 280 ms |
| P99 time-to-first-audio (slowest turns) Coval, 30-day window | 108.8 ms | 421.8 ms |
| Latency consistency (standard deviation) Coval, 30-day window | 16.6 ms | 45.6 ms |
| P50 time-to-first-audio, US East Speko | 100 ms | 121 ms |
| Accuracy: word error rate (WER) Coval, 30-day window | 4.5% | 5.8% |
| Pronunciation robustness (0 to 1) Speko | 0.3 | 0.2 |
| Speech Arena Elo (blind listener preference) Artificial Analysis | not measured | 1187 |
| Naturalness (Elo) Speko | 1579 | 1574 |
| Price per 1M characters Artificial Analysis | not measured | 49 USD |
Choose Gradium TTS Beta if…
- → Ranks 1st of 112 in the overall benchmark, against 8th for Cartesia Sonic 3.5
- → Better P50 / median time-to-first-audio: 47.2 ms vs 280 ms (Coval, 30-day window)
- → Better P99 time-to-first-audio (slowest turns): 108.8 ms vs 421.8 ms (Coval, 30-day window)
- → Better latency consistency (standard deviation): 16.6 ms vs 45.6 ms (Coval, 30-day window)
- → Better P50 time-to-first-audio, US East: 100 ms vs 121 ms (Speko)
- → Better accuracy: word error rate (WER): 4.5% vs 5.8% (Coval, 30-day window)
- → Better pronunciation robustness (0 to 1): 0.3 vs 0.2 (Speko)
- → Better naturalness (Elo): 1579 vs 1574 (Speko)
Choose Cartesia Sonic 3.5 if…
On the published benchmarks, Cartesia Sonic 3.5 wins none of the measurements above against Gradium TTS Beta. This says nothing about features the benchmarks do not measure.
Cartesia Sonic 3.5: all measurements →Frequently asked questions
- What is the difference between Gradium TTS Beta and Cartesia Sonic 3.5?
- In the 2026 TTS API benchmark, Gradium TTS Beta ranks 1st of 112 with 76.8/100 and Cartesia Sonic 3.5 ranks 8th with 58.5/100, a gap of 18.3 points on the same rules.
- Which is faster for real-time voice agents, Gradium TTS Beta or Cartesia Sonic 3.5?
- On Coval's 30-day window ending October 1, 2026, the P50 time-to-first-audio is 47.2 ms for Gradium TTS Beta and 280 ms for Cartesia Sonic 3.5; the P99 is 108.8 ms and 421.8 ms.
- On which criteria does Cartesia Sonic 3.5 beat Gradium TTS Beta?
- Cartesia Sonic 3.5 scores higher on Voice quality (15.8 vs 7.8 out of 20), Price (1.6 vs 0.5 out of 5).
- How are these two text-to-speech APIs scored?
- Both are scored by the same public rules: 4 criteria, 100 points (Real-time speed 60, Voice quality 20, Accuracy 15, Price 5), computed from three independent benchmarks: Coval, Speko and Artificial Analysis. A measurement a benchmark does not publish counts zero, and the model page says why.
- Can these numbers be checked?
- Yes. Each model page lists every measurement with its source and date, and links to the benchmark page it comes from. The rules are on the methodology page.