Data read on November 19, 2026
Gradium TTS vs Palabra palabra-tts-v1
Side by side on the four measures Coval publishes for every model. Lower is better on all four.
| Gradium TTS | Palabra palabra-tts-v1 | lower | |
|---|---|---|---|
| Median time to first audio | 64 ms | 65 ms | within 10 ms |
| P95 time to first audio (slow turns) | 172 ms | 135 ms | Palabra palabra-tts-v1 |
| Leading silence (median) | 0 ms | 0 ms | within 10 ms |
| Word error rate (mean) | 1.7% | 1.7% | Palabra palabra-tts-v1 |
Measured by Coval from US East on the same day for both models. A gap under 10 ms is within day-to-day variation.
Source : Coval · Read on November 19, 2026 · gradium-tts-beta-202609 · palabra-tts-v1