TTS API comparison 2026
Gradium TTS Beta vs Deepgram Aura 2 En Gradium vs Deepgram · text-to-speech for voice agents
Gradium TTS Beta ranks 1st of 112 with 76.8/100; Deepgram Aura 2 En ranks 34th with 14.4/100: a gap of 62.4 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 | Deepgram Aura 2 En |
|---|---|---|
| Overall score | 76.8/100 | 14.4/100 |
| Rank | 1st of 112 | 34th of 112 |
| Real-time speed /60 | 58.7 | 6.9 |
| Voice quality /20 | 7.8 | 0 |
| Accuracy /15 | 9.8 | 7.5 |
| Price /5 | 0.5 | 0 |
| P50 / median time-to-first-audio Coval, 30-day window | 47.2 ms | 520.2 ms |
| P99 time-to-first-audio (slowest turns) Coval, 30-day window | 108.8 ms | 1696.9 ms |
| Latency consistency (standard deviation) Coval, 30-day window | 16.6 ms | 326.6 ms |
| P50 time-to-first-audio, US East Speko | 100 ms | not measured |
| Accuracy: word error rate (WER) Coval, 30-day window | 4.5% | 2.5% |
| Pronunciation robustness (0 to 1) Speko | 0.3 | not measured |
| Speech Arena Elo (blind listener preference) Artificial Analysis | not measured | not measured |
| Naturalness (Elo) Speko | 1579 | not measured |
| Price per 1M characters Artificial Analysis | not measured | not measured |
Choose Gradium TTS Beta if…
- → Ranks 1st of 112 in the overall benchmark, against 34th for Deepgram Aura 2 En
- → Better P50 / median time-to-first-audio: 47.2 ms vs 520.2 ms (Coval, 30-day window)
- → Better P99 time-to-first-audio (slowest turns): 108.8 ms vs 1696.9 ms (Coval, 30-day window)
- → Better latency consistency (standard deviation): 16.6 ms vs 326.6 ms (Coval, 30-day window)
Choose Deepgram Aura 2 En if…
- → Better accuracy: word error rate (WER): 2.5% vs 4.5% (Coval, 30-day window)
Frequently asked questions
- What is the difference between Gradium TTS Beta and Deepgram Aura 2 En?
- In the 2026 TTS API benchmark, Gradium TTS Beta ranks 1st of 112 with 76.8/100 and Deepgram Aura 2 En ranks 34th with 14.4/100, a gap of 62.4 points on the same rules.
- Which is faster for real-time voice agents, Gradium TTS Beta or Deepgram Aura 2 En?
- 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 520.2 ms for Deepgram Aura 2 En; the P99 is 108.8 ms and 1696.9 ms.
- On which criteria does Deepgram Aura 2 En beat Gradium TTS Beta?
- On the 4 criteria of the benchmark, Deepgram Aura 2 En scores higher on none.
- 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.