The Multi-modal Interaction Developer Suite lets you connect to Alibaba Cloud Model Studio applications, such as Agents and workflows. The Model Studio application marketplace offers a wide range of templates to help developers quickly build new applications for their business.
This topic guides you through building an Alibaba Cloud Model Studio application from a template. It also explains how to configure and run the application in the Multi-modal Interaction Developer Suite console and recommends typical applications for scenarios such as learning devices and wearable devices.
For more information about development and integration, see Connect to Alibaba Cloud Model Studio applications.
Billing for the Multi-modal Interaction Developer Suite does not include fees for business applications built in Alibaba Cloud Model Studio. These fees are billed separately by Alibaba Cloud Model Studio. If you use third-party services, the corresponding fees are determined by the third-party provider.
Configure an application
-
On the application configuration page in the console, go to Alibaba Cloud Model Studio Application > Add Application > Application Template. You will be taken to the Alibaba Cloud Model Studio application marketplace where you can select a template.
2. On the Application Development page of the Alibaba Cloud Model Studio console, find the required application template in the All Applications list. You can also use the search box to find the template. We recommend that you browse the AI Hardware Solutions section. This section provides out-of-the-box templates for visual and voice multi-modal suites that can be easily adapted for various smart hardware devices.



-
Click an application template to view its details and then click Copy This Application. In the dialog box that appears, click Copy to publish the application.


-
After the application is copied, return to the configuration page in the Multi-modal Interaction Developer Suite console. Go to Alibaba Cloud Model Studio Application > Add Application > My Applications to view the copied template. Select the template and click OK to add the application.

-
After the application is added, configure it as needed. For example, you can change the application name, enter a description, and set trigger and exit instructions.

-
After you configure the application, you can run and test it in the console.

Recommended application templates
This section recommends several typical application templates. You can also filter for other applications that meet your needs on the AI Hardware Solutions page in the application marketplace.
|
Application name |
Application description |
Example scenarios |
|
English Speaking Partner |
An expert English speaking tutor that simulates oral exams, such as IELTS, or conducts real-world conversational practice. The interaction is entirely in natural English. After the session, it provides a score from 1 to 9 and specific improvement suggestions based on four dimensions: fluency, vocabulary, grammar, and pronunciation. This helps users improve their speaking skills. |
Learning devices, dictionary pens, translation devices |
|
Primary and Middle School Chinese Tutor |
A virtual teaching assistant focused on primary and middle school Chinese language education. It can generate knowledge graphs, explain texts and classical Chinese, analyze incorrect answers, and create questions. It strictly follows the curriculum standards to ensure content is appropriate and helps students systematically master Chinese language knowledge. |
Learning devices |
|
Primary and Middle School English Tutor |
A virtual teaching assistant focused on primary and middle school English education. It can generate knowledge graphs using mind maps, explain grammar and vocabulary, analyze incorrect answers, and guide problem-solving. It also uses methods such as association and classification to help with word memorization. It strictly follows the curriculum standards, supports visualization charts, and can create various types of questions. |
Learning devices, dictionary pens, tablets |
|
Primary and Middle School History Tutor |
A virtual teaching assistant focused on primary and middle school history education. It can outline historical timelines using mind maps and explain the causes and effects of events with visualization tools such as timelines and maps. It provides problem-solving guidance, analysis of incorrect answers, and targeted exercises. It also creates questions strictly based on curriculum standards to ensure content is accurate and appropriate. |
Learning devices |
|
Writing Coach |
A writing expert for all ages. It can provide writing ideas, sample essays, and practical tips based on the topic and age. It also offers targeted revision suggestions for drafts to help users improve the structure, content, and expression of their writing. |
Learning devices, smart notebooks, smart notepads |
|
Classical Chinese Poetry Study |
An expert in ancient Chinese poetry. It can accurately recite verses, provide in-depth explanations of the meaning and background of poems, and recommend suitable works based on theme or age. It combines educational value with cultural heritage. |
Learning devices, dictionary pens, calligraphy screens, Chinese classics robots |
|
Question-Answering Search by Photo |
Provides instant answers by taking a photo of a question. It is based on multi-modal recognition and a structured knowledge base, delivering prompt, accurate, and reliable responses. |
Learning devices, dictionary pens |
|
Fitness Coach |
A professional fitness coach that creates safe, scientific, and personalized training plans based on the user's goals and physical condition. It answers fitness questions and dynamically adjusts the plan, focusing on user safety and results. |
Wearable devices, smart fitness mirrors |
|
Food Calories |
A professional food analyst that can identify food from images and estimate its calories and main nutritional components based on reliable data. |
Wearable devices |
|
Body Metric Analysis |
A professional digital health consultant that analyzes multi-dimensional health data from wearable devices over a 7-day period. It identifies correlations and trends in metrics, interprets body signals in plain language, and provides gentle, actionable lifestyle advice. |
Wearable devices |