add Ming-omni-tts blog. by xqacmer · Pull Request #12 · inclusionAI/inclusionAI.github.io

xqacmer · 2026-03-05T03:09:11Z

No description provided.

gemini-code-assist · 2026-03-05T03:09:27Z

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request adds a new blog post introducing Ming-Omni-TTS, an innovative unified audio generation model. The post highlights the model's advanced capabilities in fine-grained speech control, zero-shot voice design, and its unique ability to generate speech, music, and environmental sounds simultaneously. It also emphasizes the model's efficiency and its capacity to handle complex text normalization, making it a versatile tool for various audio synthesis applications.

Highlights

New Blog Post: Ming-Omni-TTS: Introduced a comprehensive blog post detailing the Ming-Omni-TTS model, a high-performance unified audio generation system capable of synthesizing speech, music, and sound.
Advanced Audio Control: The model offers precise control over speech attributes such as rate, pitch, volume, emotion, and dialects, including high accuracy for Cantonese and emotional control.
Unified Generation Capabilities: Ming-Omni-TTS is noted as the industry's first autoregressive model to jointly generate speech, ambient sound, and music within a single channel, providing an immersive auditory experience.
High Efficiency and Text Normalization: It achieves competitive inference efficiency (3.1Hz) through a custom 12.5Hz continuous tokenizer and 'Patch-by-Patch' compression, alongside robust text normalization for complex mathematical and chemical expressions.
Multilingual Content: The blog post is provided in both English and Chinese versions to cater to a broader audience.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

content/blog/ming-omni-tts/index.md
- Added a new blog post in English introducing the Ming-Omni-TTS model, detailing its features, model structure, benchmark evaluations, and various generation capabilities.
content/blog/ming-omni-tts/index.zh.md
- Added a new blog post in Chinese introducing the Ming-Omni-TTS model, providing a localized version of the content with details on its technical highlights, structure, and performance.

Activity

No specific activity (comments, reviews, or progress updates) has been recorded for this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

gemini-code-assist

Code Review

This pull request adds two new blog posts, one in English and one in Chinese, for Ming-Omni-TTS. The changes introduce the model, its features, and various examples. My review focuses on improving consistency and accessibility in the markdown files. I've suggested changes to link behavior, header formatting, image alt texts, and translation consistency.

_{Note: Security Review has been skipped due to the limited scope of the PR.}

gemini-code-assist · 2026-03-05T03:11:30Z

content/blog/ming-omni-tts/index.md

+show_word_count: true
+---
+
+{{< button href="https://github.com/inclusionAI/Ming-omni-tts" label="GITHUB" external=true >}} 🤗 <a href="https://huggingface.co/inclusionAI/Ming-omni-tts-0.5B">Hugging Face</a>｜ 🤖 <a href="https://modelscope.cn/models/inclusionAI/Ming-omni-tts-0.5B">ModelScope</a>


The GitHub link opens in a new tab, but the Hugging Face and ModelScope links do not. For a consistent user experience, all external links should open in a new tab. Please add target="_blank" to the other links. It's also a good security practice to add rel="noopener noreferrer" when using target="_blank".

Suggested change

{{< button href="https://github.com/inclusionAI/Ming-omni-tts" label="GITHUB" external=true >}} 🤗 <a href="https://huggingface.co/inclusionAI/Ming-omni-tts-0.5B">Hugging Face</a>｜ 🤖 <a href="https://modelscope.cn/models/inclusionAI/Ming-omni-tts-0.5B">ModelScope</a>

{{< button href="https://github.com/inclusionAI/Ming-omni-tts" label="GITHUB" external=true >}} 🤗 <a href="https://huggingface.co/inclusionAI/Ming-omni-tts-0.5B" target="_blank" rel="noopener noreferrer">Hugging Face</a>｜ 🤖 <a href="https://modelscope.cn/models/inclusionAI/Ming-omni-tts-0.5B" target="_blank" rel="noopener noreferrer">ModelScope</a>

字体无需修饰，需保持和其他blog格式一致。

gemini-code-assist · 2026-03-05T03:11:30Z

content/blog/ming-omni-tts/index.md

+### Unified Continuous Audio Tokenizer.
+<img width="1034" alt="结构图" src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/img/W3RqRLQx8DEAAAAAUDAAAAgADvHDAQFr/original" />
+
+### Unified Audio Language Model for Speech, Music and Sound Generation.
+<img width="1034" alt="结构图" src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/img/oop7QJpDNdIAAAAAV1AAAAgADvHDAQFr/original" />


For consistency with other headers in the document, the trailing periods should be removed from the headers on lines 33 and 36. Additionally, the alt text for the images should be in English for accessibility in an English document. A more descriptive alt text is also recommended.

Suggested change

### Unified Continuous Audio Tokenizer.

<img width="1034" alt="结构图" src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/img/W3RqRLQx8DEAAAAAUDAAAAgADvHDAQFr/original" />

### Unified Audio Language Model for Speech, Music and Sound Generation.

<img width="1034" alt="结构图" src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/img/oop7QJpDNdIAAAAAV1AAAAgADvHDAQFr/original" />

### Unified Continuous Audio Tokenizer

<img width="1034" alt="Diagram of the Unified Continuous Audio Tokenizer architecture." src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/img/W3RqRLQx8DEAAAAAUDAAAAgADvHDAQFr/original" />

### Unified Audio Language Model for Speech, Music and Sound Generation

<img width="1034" alt="Diagram of the Unified Audio Language Model for Speech, Music and Sound Generation architecture." src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/img/oop7QJpDNdIAAAAAV1AAAAgADvHDAQFr/original" />

alt内容不会展示出来，无需修改。

alt 类型的内容对于 SEO 这些很重要，建议修改

gemini-code-assist · 2026-03-05T03:11:30Z

content/blog/ming-omni-tts/index.md

+<img width="1034" alt="结构图" src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/img/oop7QJpDNdIAAAAAV1AAAAgADvHDAQFr/original" />
+
+## Benchmark Evaluations
+<img width="1034" alt="结构图" src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/img/GBiVQ7tR2I4AAAAAdhAAAAgADvHDAQFr/original" />


The alt text for the image should be in English for accessibility in an English document. A more descriptive alt text related to the section 'Benchmark Evaluations' is recommended.

Suggested change

<img width="1034" alt="结构图" src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/img/GBiVQ7tR2I4AAAAAdhAAAAgADvHDAQFr/original" />

<img width="1034" alt="Table showing benchmark evaluation results." src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/img/GBiVQ7tR2I4AAAAAdhAAAAgADvHDAQFr/original" />

alt内容不会展示出来，无需修改。

alt 内容对于 SEO 类型很重要，建议修改，目前这种写法的确不是很专业

gemini-code-assist · 2026-03-05T03:11:30Z

content/blog/ming-omni-tts/index.zh.md

+show_word_count: true
+---
+
+{{< button href="https://github.com/inclusionAI/Ming-omni-tts" label="GITHUB" external=true >}} 🤗 <a href="https://huggingface.co/inclusionAI/Ming-omni-tts-0.5B">Hugging Face</a>｜ 🤖 <a href="https://modelscope.cn/models/inclusionAI/Ming-omni-tts-0.5B">ModelScope</a>


The GitHub link opens in a new tab, but the Hugging Face and ModelScope links do not. For a consistent user experience, all external links should open in a new tab. Please add target="_blank" to the other links. It's also a good security practice to add rel="noopener noreferrer" when using target="_blank".

Suggested change

{{< button href="https://github.com/inclusionAI/Ming-omni-tts" label="GITHUB" external=true >}} 🤗 <a href="https://huggingface.co/inclusionAI/Ming-omni-tts-0.5B">Hugging Face</a>｜ 🤖 <a href="https://modelscope.cn/models/inclusionAI/Ming-omni-tts-0.5B">ModelScope</a>

{{< button href="https://github.com/inclusionAI/Ming-omni-tts" label="GITHUB" external=true >}} 🤗 <a href="https://huggingface.co/inclusionAI/Ming-omni-tts-0.5B" target="_blank" rel="noopener noreferrer">Hugging Face</a>｜ 🤖 <a href="https://modelscope.cn/models/inclusionAI/Ming-omni-tts-0.5B" target="_blank" rel="noopener noreferrer">ModelScope</a>

字体无需修饰，需保持和其他blog格式一致。

Sure, 之后可以统一修订

gemini-code-assist · 2026-03-05T03:11:30Z

content/blog/ming-omni-tts/index.zh.md

+| Instruction | TTS Result |
+|---|---|
+| A motor is revving and changing gears | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/yPAnRqgKG7gAAAAAgCAAAAgADvHDAQFr"></audio> |
+| Thunder and a gentle rain | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/2YO-Qa73VAIAAAAAgCAAAAgADvHDAQFr"></audio> |
+| Continuous snoring of a person | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/wUo6TZDgEYMAAAAAgCAAAAgADvHDAQFr"></audio> |
+| Nature sounds with a frog croaking | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/ONTTTa5RbAwAAAAAgCAAAAgADvHDAQFr"></audio> |
+| A man talking as a stream of water trickles in the background | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/JrsRQbkYSasAAAAAgCAAAAgADvHDAQFr"></audio> |


This table contains English text within a Chinese document. For consistency, the table header Instruction and its content should be translated to Chinese. The header TTS Result could also be translated.

Suggested change

| Instruction | TTS Result |

|---|---|

| A motor is revving and changing gears | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/yPAnRqgKG7gAAAAAgCAAAAgADvHDAQFr"></audio> |

| Thunder and a gentle rain | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/2YO-Qa73VAIAAAAAgCAAAAgADvHDAQFr"></audio> |

| Continuous snoring of a person | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/wUo6TZDgEYMAAAAAgCAAAAgADvHDAQFr"></audio> |

| Nature sounds with a frog croaking | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/ONTTTa5RbAwAAAAAgCAAAAgADvHDAQFr"></audio> |

| A man talking as a stream of water trickles in the background | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/JrsRQbkYSasAAAAAgCAAAAgADvHDAQFr"></audio> |

| 指令 | TTS 结果 |

|---|---|

| 马达转速变化和换挡声 | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/yPAnRqgKG7gAAAAAgCAAAAgADvHDAQFr"></audio> |

| 雷声和细雨声 | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/2YO-Qa73VAIAAAAAgCAAAAgADvHDAQFr"></audio> |

| 持续的鼾声 | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/wUo6TZDgEYMAAAAAgCAAAAgADvHDAQFr"></audio> |

| 带有蛙鸣的自然声音 | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/ONTTTa5RbAwAAAAAgCAAAAgADvHDAQFr"></audio> |

| 背景有水流声的男人说话声 | <audio controls src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/file/JrsRQbkYSasAAAAAgCAAAAgADvHDAQFr"></audio> |

goodcase内容本身无需中文化。

richardbsk · 2026-03-06T15:31:37Z

alt text 的反馈其实是个有用的反馈，建议修改一轮。其他的可以跟其他 blog 统一进行修订。

richardbsk · 2026-03-09T16:23:44Z

感谢修订

add Ming-omni-tts blog.

8063200

gemini-code-assist bot reviewed Mar 5, 2026

View reviewed changes

update Ming-omni-tts blog.

718ca64

richardbsk merged commit b85acd4 into inclusionAI:main Mar 9, 2026
1 check passed

	{{< button href="https://github.com/inclusionAI/Ming-omni-tts" label="GITHUB" external=true >}} 🤗 <a href="https://huggingface.co/inclusionAI/Ming-omni-tts-0.5B">Hugging Face</a>｜ 🤖 <a href="https://modelscope.cn/models/inclusionAI/Ming-omni-tts-0.5B">ModelScope</a>
	{{< button href="https://github.com/inclusionAI/Ming-omni-tts" label="GITHUB" external=true >}} 🤗 <a href="https://huggingface.co/inclusionAI/Ming-omni-tts-0.5B" target="_blank" rel="noopener noreferrer">Hugging Face</a>｜ 🤖 <a href="https://modelscope.cn/models/inclusionAI/Ming-omni-tts-0.5B" target="_blank" rel="noopener noreferrer">ModelScope</a>

	<img width="1034" alt="结构图" src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/img/GBiVQ7tR2I4AAAAAdhAAAAgADvHDAQFr/original" />
	<img width="1034" alt="Table showing benchmark evaluation results." src="https://mdn.alipayobjects.com/huamei_7mmngh/afts/img/GBiVQ7tR2I4AAAAAdhAAAAgADvHDAQFr/original" />

Conversation

xqacmer commented Mar 5, 2026

Uh oh!

gemini-code-assist bot commented Mar 5, 2026

Summary of Changes

Highlights

Footnotes

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist bot Mar 5, 2026

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Mar 5, 2026

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Mar 5, 2026

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Mar 5, 2026

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Mar 5, 2026

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

richardbsk commented Mar 6, 2026

Uh oh!

richardbsk commented Mar 9, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants