Recording Summary Agent tutorial

Updated at:

The Recording Summary Agent provides real-time speech transcription and recording summary capabilities for multimodal applications in Model Studio. Use this agent to transcribe speech in real time, generate meeting summaries, and view intelligent analysis results through the Tingwu service.

Feature entry

After you create a multimodal application, go to Multimodal Interaction Console > Agent > Recommended Applications, select Recording Summary and click Confirm to add it.

Activate the service

When you use the Recording Summary Agent for the first time, you must activate the Tingwu service. Go to Tingwu - Intelligent Summary to activate the service and publish the application.

  1. In the Tingwu - Intelligent Summary application, click Activate Now in the upper-right corner.

On the activation page, select Tingwu Agent Pay-As-You-Go and click Buy Now to complete the activation.

On the order confirmation page, confirm the Tingwu Agent Service order information (billing method: Pay-As-You-Go). Read and agree to the Product Service Agreement and Service Level Agreement, then click Activate Now to complete the activation.

  1. After you complete the activation, click Create Application in the upper-right corner of the Tingwu - Intelligent Summary console to configure and publish the application.

Complete the following settings on the Debug Configuration tab:

  1. In Select Audio Input Method, select the desired mode (for example, Real-time Transcription).
  2. Select the Transcription Model (for example, paraformer-v2).
  3. In Transcription Configuration, set the number of Speaker Separation speakers and Recognition Language.
  4. In the Translation area, set the Content Translation target language.

After the configuration is complete, click Publish in the upper-right corner to publish the application.

Configure the application

After you create and publish an application in the Tingwu - Intelligent Summary console, you must select the corresponding Tingwu application on the Multimodal Interaction Console page. To adjust application capabilities, you can go to the Tingwu - Intelligent Summary console to make the changes configure.

Real-time recording summary settings

In the right-side configuration panel, you can set the start command, exit/pause wake word, and resume command for real-time recording summary.

Exit/pause wake word: During recording, the system checks whether to exit or pause recording only after the wake word is recognized, which prevents accidental exits. The default wake word is Xiao Yun. (Recommended) Add the wake word to Tingwu's hot words to improve recognition accuracy. Each command supports clicking + to add multiple entries, with a character limit of 100.

Representative commands:

Start command

Pause command (custom wake word)

Resume command

Exit command (custom wake word)

"Start/Open/Enable real-time transcription"

"Start real-time transcription"

"Start real-time transcription and translate"

"Start real-time transcription of the meeting content"

"Open real-time transcription and record this conversation"

"Start real-time transcription now"

"Start real-time transcription and record the discussion"

"Open real-time transcription to record the class content"

"Start real-time transcription of the customer consultation"

"Start real-time transcription and record the group discussion"

"Transcribe this conversation in real time now"

"Xiao Yun, pause for a moment"

"Xiao Yun, pause transcription"

"Xiao Yun, pause real-time transcription"

"Xiao Yun, wait before continuing real-time transcription"

"Xiao Yun, stop transcribing for now"

"Xiao Yun, transcription paused"

"Continue recording"

"Continue real-time transcription"

"Continue transcription"

"You can continue transcribing"

"Resume transcription"

"Go ahead and transcribe"

"Xiao Yun, stop transcription"

"Xiao Yun, end transcription"

"Xiao Yun, stop real-time transcription"

"Xiao Yun, end real-time transcription"

"Xiao Yun, end transcription and organize the content for me"

"Xiao Yun, stop transcription and summarize this discussion"

"Xiao Yun, stop real-time transcription and summarize the current conversation"

Recording file summary settings

You can also set the start command, exit command, pause command, and resume command for recording file summary.

Representative commands:

Start command

Exit command

Pause command

Resume command

"Start/Open/Enable recording summary"

"Start recording and summarize"

"Record and summarize this meeting"

"Start recording and summarize now"

"Start recording and summarize the class content"

"Record and summarize the upcoming interview"

"Record and summarize this discussion"

"Open recording and summarize the current conversation"

"Record and summarize the current meeting content"

"Record and summarize this customer consultation"

"Record and summarize the group discussion"

"Start recording and summarize this conversation"

"Record the class content and summarize"

"Stop recording"

"End recording"

"End recording, help me summarize it, and translate it into English"

"End recording and organize this discussion"

"Stop recording and summarize today's class"

"End the meeting recording and translate it into English"

"Wait before recording"

"Pause recording"

"Stop recording for now"

"Recording paused"

"Continue recording"

"Continue the recording"

"You can continue recording"

"Resume recording"

"Go ahead and record"

Conversation experience

After you complete all configurations, you can experience Tingwu's recording and meeting summary capabilities in the Multimodal Interaction Console.

Start real-time transcription

Use the start command configured earlier to start the recording summary, for example, "Enable real-time transcription". Transcription starts, and you can also view bilingual subtitles.

After you send the command, the system displays meeting_state_change command sent successfully. The AI confirms that real-time speech-to-text has been enabled and states that a recording summary will be automatically generated after transcription ends. A real-time transcription area appears at the bottom of the voice interaction experience panel on the right, displaying transcription timing and the Single/Complete toggle buttons.

Exit real-time transcription

Use the wake word combined with the exit command configured earlier to exit real-time transcription, for example, "Xiao Yun, exit real-time transcription". Click View Analysis Results to go to Tingwu and view the intelligent summary.

The left side of the Tingwu Intelligent Summary page displays the speech-to-text transcription and translation results of the conversation, with playback controls at the bottom (including the play button, progress bar, and speed settings). The right side is the analysis results area, which contains three tabs: Quick Overview, Mind Map, and Custom Prompt, where you can view intelligent analysis results such as automatically extracted keyword tags, full-text summaries, chapter overviews, and key point reviews.