Ant's inclusionAI Open-Sources Five Ming-3.0 Speech Models

Ant Group's inclusionAI (AntLingAGI) open-sourced five Ming-3.0 voice models on Hugging Face and ModelScope on October 19–20. All use a MoE architecture, ranging from 0.5B to 126B total parameters (6.5B activated), with weights released under MIT and Day-0 inference support via vLLM-Omni.

Confirmed

Ming-3.0-tts family: tts-0.5B supports voice design and paralinguistic cues; tts (7.9B, 1.3B activated) excels at long-form speech generation; a post also mentions tts-tiny (9B) text-to-speech specs.
Ming-3.0-audio family: audio-tiny is a 9.3B compact native audio language model that takes audio + text instruction input, supporting speech recognition, spoken Q&A, audio understanding and reasoning, with optional built-in or reference voices for speech synthesis; audio-flash has 126B total / 6.5B activated parameters, supporting audio understanding + speech output.
The series covers controllable speech synthesis, long-recording analysis, and context-aware transcription.
According to @AdinaYakup and the repost by @realmrfakename, Ming-3.0-tts-0.5B tops the open-source TTS ranking on the Artificial Analysis Controlled Voice leaderboard, with voice cloning reaching open-source SOTA (from ModelScope release info, not independently verified).

Why It Matters

Open-sourcing a complete model family spanning TTS, ASR, and audio understanding in one go under MIT, with Day-0 vLLM-Omni support, lowers the barrier for community deployment and further development.
The spec range from 0.5B to 126B-A6.5B covers both edge and high-capability scenarios, and combined with leaderboard results, forms a strong open-source alternative to closed voice models.

2026-10-19 ~ 2026-10-20 · 6 related posts

Primary sources

Ant open-sources five Ming-3.0 MoE speech models with day-0 vLLM-Omni support — vllm_project · 2026-10-20 00:26 (UTC+08:00)
Ant Group open-sources Ming-3.0 speech models, tops Artificial Analysis open TTS leaderboard — AdinaYakup · 2026-10-20 00:23 (UTC+08:00)
inclusionAI Releases Ming-3.0-audio-flash: 126B MoE Audio Model, MIT — BerryBlush_Rogers691 · 2026-10-19 22:42 (UTC+08:00)

inclusionAI open-sources Ming-3.0-audio-tiny: 9.3B MoE audio-language model (MIT) — jacek2023 · 2026-10-19
[source] inclusionAI Releases Ming-3.0-audio-flash: 126B MoE Audio Model, MIT — BerryBlush_Rogers691 · 2026-10-19
Ming-3.0 ships five open-weight audio models with open SOTA voice cloning — realmrfakename · 2026-10-19
[source] Ant Group open-sources Ming-3.0 speech models, tops Artificial Analysis open TTS leaderboard — AdinaYakup · 2026-10-20
[source] Ant open-sources five Ming-3.0 MoE speech models with day-0 vLLM-Omni support — vllm_project · 2026-10-20

1 near-duplicate retellings: AccBalanced