> 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/maiagent-user-guide-en/meeting-records/live-transcription.md).

# Live Meeting Transcription

Live mode provides low-latency voice transcription and translation, allowing you to see the real-time transcript while the meeting is in progress.

## Start Recording

After creating a meeting record, click "Start Recording" to begin live transcription.

The system will:

1. Create a real-time communication room (LiveKit)
2. Start the speech recognition engine
3. Begin receiving microphone audio and transcribing in real time

## Transcription View

During recording, the screen displays in real time:

* **Recording Timer**: Shows the elapsed recording time
* **Live Transcript**: Speech recognition results appear on screen in real time
* **Speaker Labels**: Indicate the speaker for each text segment
* **Language Tags**: Display the original language of each text segment
* **Translation Results**: If translation is enabled, translated text appears below the original text
* **Transcription Statistics**: Number of completed segments, in-progress segments, and total word count

## Low-latency Real-time Transcription

The core feature of live mode is low latency — transcribed text appears on screen within seconds of speaking, allowing participants to verify the record in real time.

## Low-latency Real-time Translation

When translation is enabled, the system translates content into the specified target languages simultaneously with transcription, also with low latency:

* Supports up to **3 target languages** for simultaneous translation
* Translation is processed in real time by the selected LLM model
* Translation results are attached below each transcript segment
* Ideal for international meetings and multilingual team communication

## Controls

| Control               | Description                                                  |
| --------------------- | ------------------------------------------------------------ |
| **Microphone Toggle** | Temporarily mute or unmute the microphone                    |
| **Stop Recording**    | End the meeting recording; the system begins post-processing |
| **Search Transcript** | Search for keywords in the live transcript                   |

## After Recording Ends

After clicking "Stop Recording," the meeting status changes to "Processing" and the system performs the following in the background:

1. **Audio Conversion**: Convert the raw audio to MP3 format
2. **Transcript Organization**: Organize live transcription results into a structured transcript file
3. **Cloud Storage**: Upload the audio and transcript to S3 storage

Once processing is complete, the status automatically updates to "Completed," and you can access the meeting detail page to view the full content.


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.maiagent.ai/maiagent-user-guide/maiagent-user-guide-en/meeting-records/live-transcription.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.