Gradium TTS Gradium · text-to-speech (TTS) API

Speed

On Coval's 30-day window ending October 27, 2026 (2,808 runs from US East), Gradium TTS starts speaking after 53.7 ms on a typical turn (median) and 104.3 ms on a slow turn (P95, the slowest one in twenty). That P95 is 4th lowest of the 31 models Coval measures, which puts it in the Headroom tier: headroom to spend elsewhere in the turn. On the median it is a tie (gap under 10 ms) with Alibaba Qwen3 TTS Fast and Inworld Realtime TTS-2 Flash. Speko's board plots it at 55 ms time to first audio from US East; its model page reports a 105 ms sweep. Cekura measures 76 ms (median) from sending a full sentence to the first sound (2nd lowest of the 26 models Cekura measures), and 64 ms before the last word arrives when the text is streamed word by word.

Voice quality

Speko rates its naturalness at 1,592 Elo from blind A/B votes on phone-agent lines (6th highest of the 43 models Speko rates). In the Artificial Analysis Speech Arena it holds 1,174 ±13 Elo (95% interval), 21st highest of the 73 models Artificial Analysis rates; scores whose intervals overlap are a tie. In its Customer Service category, Artificial Analysis places it 19th, at 1,241 Elo. Cekura estimates its naturalness at 4.51 out of 5 with a listener model, not human votes.

Accuracy

Speko's pronunciation test on numbers, dates and currency scores it 0.27 on a 0-to-1 scale (18th highest of the 30 models Speko scores). Cekura's transcribers score its reading of hard text at 79.5% (11th highest of the 18 models Cekura scores): 77% on numbers and shorthand, 77% on codes and addresses. The tests differ, so the figures are shown side by side and never combined.

Price

Artificial Analysis lists $47.8. Speko lists about $57.8. Cekura lists $36. List prices, as each source prints them: a range of $36 to $57.8.

Languages tested

Tested in Spanish, German, French and Portuguese by Artificial Analysis or Speko. A language missing here was not tested, which does not mean it is unsupported.