AntTech
Oct 19, 2026 · Artificial Intelligence
Ming-3.0 Speech Series Open-Sourced: 5 Models for TTS, Audio Understanding & ASR
Ant Group's Ming-3.0 open-source speech series includes five models for synthesis, audio understanding, and recognition, featuring director-mode emotion control, paralinguistic tags, low-frame-rate architecture, context-aware ASR with hotwords, and top benchmark scores on MMAU, VoiceBench, and BigBenchAudio.
ASRMing-3.0TTS
0 likes · 11 min read