A
Ant Group text-to-speech models & pricing
1 model listed · appears on 1 of 3 boards
Models on the boards
ModelReleased$/1M charsBoardsComposite
Ming-3.0-ttsOct 2026—1/353.0
Latency from public benchmarks
Time to first audio, in milliseconds, as each benchmark publishes it. We don't measure latency ourselves, and the sources measure differently (harness, region, sample size), so each figure stays under its own source. Not part of the composite score.
None of the latency benchmarks we read lists a Ant Group model yet.
Coval: Time to first audio, p50, us-east-1, read Nov 22, 2026 · Speko: Time to first audio, p50, US East, read Nov 22, 2026 · Humanness Index: Time to first audio, median, read Nov 22, 2026. How latency is sourced.