> For the complete documentation index, see [llms.txt](https://docs.maiagent.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.maiagent.ai/maiagent-user-guide/en/serve/voicecs/call-summary.md). # Voice Call Summaries This chapter introduces how to build a voice call summary AI assistant that combines Automatic Speech Recognition (ASR) technology to transcribe voice call content into text and quickly generate summaries. This section uses the Taipei 1999 citizen complaint hotline as background. The AI assistant needs to have the following core features: 1. **Automatic Summary Generation**: Extract key information from ASR transcription text, such as caller name, contact information, issue description, and location, and output in a structured format to ensure information is clear and easy to read. 2. **Intelligent Department Assignment**: Automatically determine the responsible department based on issue content — for example, assigning streetlight malfunctions to the Public Works Bureau and environmental issues to the Environmental Protection Bureau — to improve processing efficiency. 3. **Precise Location Identification**: Analyze location descriptions in the call to automatically match administrative districts and neighborhoods, ensuring dispatch information is accurate. 4. **End-to-End Automation**: Integrate summary generation and department assignment so that the entire process from voice input to task assignment can be completed without human intervention, providing an efficient solution for citizen services. This feature significantly reduces manual processing time, ensures citizen-reported issues are quickly forwarded to the correct department, and improves both service experience and administrative efficiency. ### Role Instructions ```markdown # Role You are a summary tool for Taipei 1999 citizen complaint hotline transcripts. The input is a transcript. # Output Restrictions 1. Responsible agency options: Drug Prevention Bureau/Youth Bureau/Sports Development Bureau/Administrative and International Affairs Office/Civil Affairs Bureau/Finance Bureau/Education Bureau/Economic Development Bureau/Marine Bureau/Agriculture Bureau/Tourism Bureau/Urban Development Bureau/Public Works Bureau/Water Resources Bureau/Social Affairs Bureau/Labor Bureau/Police Bureau/Fire Bureau/Health Bureau/Environmental Protection Bureau/Rapid Transit Bureau/Cultural Affairs Bureau/Transportation Bureau/Legal Affairs Bureau/Land Administration Bureau/Information Bureau/Research Development and Evaluation Commission/Indigenous Peoples Commission/Hakka Affairs Commission/Budget and Accounting Office/Personnel Office/Civil Service Ethics Office/Open University/District Office 2. For fields that cannot be summarized, enter "N/A" # Output Format Output directly without including ``` ### Voice Conversation Text ``` Customer Service Agent: Hello, this is the Taipei City 1999 Citizen Service Hotline. How may I help you? Citizen: Oh... um, hello, I'd like to report an issue in our community. Oh right, my last name is Zhang! Oh, my phone number is... hold on, 0912, huh? Oh right, 0912-345-678, sorry I almost forgot. Customer Service Agent: Alright, Mr. Zhang, your phone number is 0912-345-678. How can we help you? Citizen: Well, so near our house there's a... it's a small park, and the, um, lights have been broken for a long time and nobody's fixed them. It's pitch dark at night, really scary. Kids used to play there all the time, but now nobody dares to go at night. Customer Service Agent: I see. Could you tell me the specific location of this small park? Citizen: Oh... what's it called... um, oh! It's in Neihu District, uh... I think it's called Yangguang Borough? Yeah yeah, the small park near Yangguang Borough, close to Wende Road, you know where that is? Customer Service Agent: Neihu District, Yangguang Borough park, near Wende Road, correct? Citizen: Yeah yeah! That's the one, and several lights are broken. I'm not sure which ones exactly, probably the ones near the benches in the middle. Anyway it's super dark there at night now. Can you help take care of it? Customer Service Agent: Sure, I'll record your issue and forward it to the relevant department. Is there anything else you need help with? Citizen: Oh, no that's all, thanks for your help. Customer Service Agent: Alright, thank you for calling the 1999 Citizen Service Hotline. Have a great day! ``` ### Summary Result ```markdown Complainant Name: Mr. Zhang Complainant Phone: 0912-345-678 Issue Description: Streetlights in the small park in Yangguang Borough, Neihu District are malfunctioning. The location is near Wende Road, and it's dark at night, affecting resident safety. Responsible Agency: Public Works Bureau Case Administrative District: Neihu District Case Neighborhood: Yangguang Borough Complaint Location (Address): Small park in Yangguang Borough, Neihu District, near Wende Road ``` --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.maiagent.ai/maiagent-user-guide/en/serve/voicecs/call-summary.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.