---
type: "post"
id: "ant-group-released-ming-3-0-tts-0-0b239e"
slug: "ant-group-released-ming-3-0-tts-0-0b239e"
title: "Ant Group released Ming-3.0-tts-0.5B , a dense MIT-licensed TTS model built on Qwen2.5-0.5B."
description: "InclusionAI has published Ming-3.0-tts-0.5B on Hugging Face under the MIT license."
retrieval_nugget: "InclusionAI has published Ming-3.0-tts-0.5B on Hugging Face under the MIT license."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["generative-media","multimodal"]
entities: ["Ant Group","InclusionAI","Ming-3.0-tts-0.5B","Qwen2.5-0.5B","Hugging Face"]
related_patterns: ["generative-media-becomes-application-infrastructure"]
novelty_label: "new_fact"
what_changed: "Ant Group released a distinct dense 0.5B TTS model built on Qwen2.5-0.5B, adding a new model and architecture to prior TTS release coverage."
prior_refs: ["memory:90891527-431b-81b6-a9fc-2face566c3db","memory:1b6aeacd-9c54-8f2c-a7a0-fe583f442108"]
source_url: "https://huggingface.co/inclusionAI/Ming-3.0-tts-0.5B"
source_urls: ["https://huggingface.co/inclusionAI/Ming-3.0-tts-0.5B"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:ant-group-released-ming-3-0-tts-0-0b239e"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/ant-group-released-ming-3-0-tts-0-0b239e/","markdown":"https://newruntime.com/posts/ant-group-released-ming-3-0-tts-0-0b239e.md","json":"https://newruntime.com/posts/ant-group-released-ming-3-0-tts-0-0b239e.json"}
---

# Ant Group released Ming-3.0-tts-0.5B , a dense MIT-licensed TTS model built on Qwen2.5-0.5B.

## Retrieval answer

InclusionAI has published Ming-3.0-tts-0.5B on Hugging Face under the MIT license.

InclusionAI has published Ming-3.0-tts-0.5B on Hugging Face under the MIT license. The dense text-to-speech checkpoint is described as built on a Qwen2.5-0.5B backbone and supports Chinese, English, German, Spanish, French, Korean, and Japanese; Sichuanese and Cantonese are listed as dialects.

The model card lists 44.1 kHz output, zero-shot voice cloning from a short reference clip, voice design from a natural-language speaker description, and free-form delivery control. It also lists more than 100 built-in Chinese voices, five built-in English voices, and 14 inline tags for sounds such as breathing, coughing, laughter, and hesitation.

The Hugging Face repository distributes the checkpoint, including the backbone, DiT head, audio tokenizer, speaker encoder, and text tokenizer. It is not a standalone inference setup: the card says users must obtain dependencies and inference code from the separate Ming-3.0-tts GitHub repository. The source does not establish independent quality rankings, latency, hardware requirements, or suitability for a specific production deployment.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Generative Media](https://newruntime.com/topics/generative-media.md): Explore the generative-media topic hub.
- topic hub: [Multimodal](https://newruntime.com/topics/multimodal.md): Explore the multimodal topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)