Model card
Gradium TTS.
GradiumText-to-speechProprietary neural TTS1 current SOTA
Measured 4.412 UTMOS, 13.4% hard-prompt WER, ~200ms TTFB, streaming and voice cloning.
§ 02 · Benchmarks
Every benchmark Gradium TTS has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | codesota-tts-hardtext-v2 | Audio & Speech · Text-to-Speech | critical_entity_accuracy | 0.7% | #1 | 2026-05-17 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where Gradium TTS actually performs.
§ 06 · Sources & freshness
Where these numbers come from.
codesota-run
1
result
1 of 1 rows marked verified.