Ant Group's Ant Ling open sources five Ming 3.0 speech models for text to speech, audio understanding and transcription
Today, we're open-sourcing 5 Ming-3.0 models across 3 speech families. - Ming-3.0-tts: 0.5B voice design & paralinguistic cues; Tiny 7.9B A1.3B long-form speech. - Ming-3.0-audio: Flash 126B A6.5B understanding & tools; Tiny 9.3B A2.7B efficient dialogue. - Ming-3.0-asr: Tiny 8.6B A2B dialects & context.
Context
Open weights speech models that rank near the top of public text to speech leaderboards give developers a free alternative to paid voice services from larger labs.
Ant Ling is the AI model arm of Ant Group's AGI initiative, publishing under inclusionAI. The benchmark charts are self reported by Ant Ling, though two of them are drawn from the Artificial Analysis leaderboards.
Deep dive
On October 19, Ant Ling posted that it is open sourcing five Ming 3.0 models across three speech families. It listed a 0.5 billion parameter text to speech model for voice design and paralinguistic cues, a Tiny text to speech model with 7.9 billion total and 1.3 billion active parameters for long form speech, a Flash audio model with 126 billion total and 6.5 billion active parameters for understanding and tool use, a Tiny audio model for efficient dialogue, and a Tiny speech recognition model with 8.6 billion total and 2 billion active parameters for dialects and context.
The overview slide says the text to speech models handle voice design, voice cloning and natural language control of delivery across seven languages and two dialects, while the speech recognition model handles dialect recognition, hotword lists and conversation context.
In Ant Ling's charts, the text to speech model leads an Artificial Analysis pronunciation robustness chart at 93.2 percent, ranks first on an open weights leaderboard using cloned voices and third on one using provider voices. Its own charts show the Flash audio model ahead of Seed 2.0 Lite and Mimo V2.6 Pro on several audio benchmarks but behind Qwen3.8 Omni Flash or Gemini 3.8 Flash on some.
OrcaRouter, which tracks model releases, noted that some weights had been on Hugging Face since September with little attention before the code and this announcement arrived.
What to expect next
Watch whether developers adopt the Ming 3.0 models, measured by Hugging Face downloads and third party integrations, since OrcaRouter found early downloads were low. Independent tests of voice cloning quality and dialect recognition will show whether the leaderboard positions hold up. The open weights also raise the usual question of misuse for voice cloning, so watch for any safeguards or license terms Ant Group adds as the models spread.