> 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/work/meeting-records/create-meeting.md).
# Create Meeting Records
Create a meeting record: create a new meeting, choose a speech recognition provider (STT), configure live translation, link a knowledge base, and manage existing meeting records.
## Create a New Meeting
1. Go to the "Meeting Records / Live Transcription" page
2. Fill in the following information:
| Field | Description | Required |
| ------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------- |
| **Meeting Name** | The meeting title, to make it easy to search for and identify later | Yes |
| **Participants** | Select from organization members; added members automatically receive viewing access to this meeting | No |
| **External Participants** | Customers, vendors, and other people who are not organization members. Enter a name and press Enter. They are recorded only in the meeting information and do not receive viewing access. See [Meeting Access Control](/maiagent-user-guide/en/work/meeting-records/access-control.md#external-participants) for details | No |
| **Speech Recognition Provider** | Select the speech-to-text (STT) engine | Yes |
| **Language** | The languages used in the meeting (up to 3) | Yes |
## Select a Speech Recognition Provider
The system provides STT (Speech-to-Text) engines from multiple providers, each with different language support and recognition quality:
| Engine | Features |
| ------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Deepgram** | High-quality real-time transcription, supports multiple languages |
| **Azure** | Microsoft speech services, excellent Chinese and English recognition |
| **AssemblyAI** | High accuracy, ideal for English scenarios |
| **WhisperLive** | Based on OpenAI Whisper, supports a wide range of languages |
| **Bronci** | Customized engine |
| **OpenAI gpt-live-transcribe** | OpenAI's real-time transcription model; choose one recognition language per meeting (auto-detect, Traditional Chinese, Simplified Chinese, English, Japanese, or Korean). See [below](#openai-live-transcribe) for details |
Different engines support different languages and numbers of languages. After you select an engine, the system automatically displays the available language list.
### OpenAI gpt-live-transcribe
* **Only one recognition language can be selected.** If multiple languages will be mixed during the meeting, choose auto-detect. If you choose Traditional Chinese, the transcript is output in Traditional Chinese.
* **Speaker diarization**: The real-time transcript from this engine does not include word-level timestamps, so it cannot be combined with speaker diarization. For meetings that need to distinguish speakers, choose a different engine.
* **Final result after the meeting ends**: After you stop recording, the system reports the final transcription result for the meeting and reloads the saved transcript. See [Live Meeting Records: After Recording Ends](/maiagent-user-guide/en/work/meeting-records/live-transcription.md#final-transcription-result).
* The engine list is enabled by the platform. If this option does not appear in the list, contact your MaiAgent representative.
## Configure Live Translation (Optional)
If participants use different languages, you can enable live translation:
1. Turn on the "Enable Translation" toggle
2. Select the target translation languages (up to 3)
3. Select the LLM model to use for translation
Translation runs at the same time as transcription, and the transcript displays both the original text and the translation.
## Link a Knowledge Base (Optional)
You can specify a knowledge base to link when you create the meeting. After the meeting ends, you can upload the transcript to the knowledge base with one click, so that the Agent can reference the meeting content.
## Manage Meeting Records
On the meeting list page, you can:
* **Search**: Search by meeting name
* **Filter**: Filter by status (Pending, Recording, Processing, Completed, Failed)
* **Date Range**: View meetings within a specified time range
* **Edit**: Modify the meeting name, language settings, translation settings, and knowledge base link
* **Delete**: Remove meeting records you no longer need
---
# 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/work/meeting-records/create-meeting.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.