---
type: "post"
id: "inclusionai-open-sourced-five-ming-3-0-speech-0bcc34"
slug: "inclusionai-open-sourced-five-ming-3-0-speech-0bcc34"
title: "InclusionAI open-sourced five Ming-3.0 speech models under MIT across TTS, audio, and ASR families."
description: "InclusionAI has updated its Ming-3.0 collection on Hugging Face with five speech-model repositories."
retrieval_nugget: "InclusionAI has updated its Ming-3.0 collection on Hugging Face with five speech-model repositories."
published_at: "2026-10-25"
updated_at: "2026-10-25"
record_date: "2026-10-25"
date_kind: "published_at"
topics: ["models"]
entities: ["InclusionAI","Ming-3.0","Hugging Face","Ming-3.0-audio-flash","Ming-3.0-asr-tiny","Ming-3.0-tts-tiny"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "The release expands from the prior single Ming-3.0-tts-0.5B checkpoint to a five-model collection spanning TTS, audio, and ASR."
prior_refs: ["memory:d5355848-4a4c-8b5a-ae79-5b8538be9eff","memory:535a3824-2bff-85a7-a760-338eb5f04a67"]
source_url: "https://huggingface.co/collections/inclusionAI/ming-30"
source_urls: ["https://huggingface.co/collections/inclusionAI/ming-30"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:inclusionai-open-sourced-five-ming-3-0-speech-0bcc34"
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/inclusionai-open-sourced-five-ming-3-0-speech-0bcc34/","markdown":"https://newruntime.com/posts/inclusionai-open-sourced-five-ming-3-0-speech-0bcc34.md","json":"https://newruntime.com/posts/inclusionai-open-sourced-five-ming-3-0-speech-0bcc34.json"}
---

# InclusionAI open-sourced five Ming-3.0 speech models under MIT across TTS, audio, and ASR families.

## Retrieval answer

InclusionAI has updated its Ming-3.0 collection on Hugging Face with five speech-model repositories.

InclusionAI has updated its Ming-3.0 collection on Hugging Face with five speech-model repositories. The collection page lists Ming-3.0-audio-flash, Ming-3.0-audio-tiny, Ming-3.0-asr-tiny, Ming-3.0-tts-tiny, and Ming-3.0-tts-0.5B.

The listed tasks span text-to-speech, automatic speech recognition, and an audio model. Hugging Face displays 128B for audio-flash, 9B for audio-tiny, asr-tiny, and tts-tiny, and 1B for the repository named tts-0.5B. The collection page was updated four days earlier; individual repositories shown there were updated three or four days earlier.

The collection itself does not establish the models' licence terms, supported languages, training data, benchmark results, inference requirements, or production suitability. It also does not provide enough information to verify claims about openness beyond the repositories being listed publicly on Hugging Face. No release date, pricing, access limits, or deployment documentation is given on the collection page.

Source: https://huggingface.co/collections/inclusionAI/ming-30

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: [Models](https://newruntime.com/topics/models.md): Explore the models 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)