Ant Group open-sources Ming-3.0 speech models, tops Artificial Analysis open TTS leaderboard
AdinaYakup · x · 2026-10-20
Ant Group's Ant Ling AGI released the Ming-3.0 speech model family on Hugging Face and ModelScope, spanning several sizes:
- Ming-3.0-tts-0.5B / tts-tiny (9B): text-to-speech
- Ming-3.0-audio-flash (128B) / audio-tiny (9B): audio understanding
- Ming-3.0-asr-tiny (9B): speech recognition
Per the Artificial Analysis leaderboard chart shared with the post, Ming-3.0-tts is a strong showing: it ranks #1 among open-weights TTS models on the controlled-voice board with an Elo of 1069, ahead of Fish Audio Drama 3 Preview (1059) and Breeze TTS 2 (1018), and #3 on the provider-voices board (Elo 1188). It also tops the English pronunciation robustness test at 93.2%, tied with Fish Audio Drama 3 Preview.
Related event: Ant's inclusionAI Open-Sources Five Ming-3.0 Speech Models(6 posts)→
More from Models
- Black Forest Labs Launches FLUX 3 Max: 10-Second Videos in 12s, 22x Faster Than Seedance 2.5 — bfl_ai · 2026-10-20
- Smaug Open-Sources SOTA AI Image Detector, Hits 86.7% Recall at 5% False Alarms — bindureddy · 2026-10-20
- Anthropic Email Reveals Claude Mythos 5.1, Opus 5.5, Sonnet 5.5 in Expanded Cyber Verification Program — Sauers_ · 2026-10-20
- Dream-1 launches: 41% of subtasks in 5 minutes, outpacing top LLM agents — gharik · 2026-10-20
- Xiaomi's MiMo-V2.6-Pro is 'the first LLM that thinks like a teenager' — and it's actually good — hrishioa · 2026-10-20
- Cloudflare ships a new 'extraction model': unstructured data in, fields with probabilities out — ritakozlov · 2026-10-20