Ant Group's Ming-3.0 Quietly Tops Open-Source Speech Benchmarks at 93.2%
Ant Group quietly dropped an MIT-licensed 0.5B TTS model that ties Fish Audio for #1 pronunciation accuracy and leads all open weights in voice cloning.
Source
Artificial Analysis
Published
Author
AlphaSignal Newsroom
Read
1 min read
Ant Group quietly dropped an MIT-licensed 0.5B TTS model that ties Fish Audio for #1 pronunciation accuracy and leads all open weights in voice cloning.
Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.
