> ## Documentation Index
> Fetch the complete documentation index at: https://docs.enconvo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Meeting & Lecture Recording

> Record, transcribe, and analyze meetings and lectures with AI

## Overview

EnConvo's Meeting and Lecture Recording feature turns your Mac into an intelligent recording assistant. Record audio from meetings, lectures, interviews, or any conversation, then get automatic transcriptions, AI-generated summaries, and the ability to ask questions about the content -- all processed locally on your Mac for maximum privacy.

## Key Capabilities

<CardGroup cols={2}>
  <Card title="Audio Recording" icon="microphone">
    Record system audio, microphone input, or both simultaneously
  </Card>

  <Card title="Automatic Transcription" icon="closed-captioning">
    Convert speech to text with speaker identification
  </Card>

  <Card title="AI Summaries" icon="file-lines">
    Get structured summaries with key points and action items
  </Card>

  <Card title="Q&A on Recordings" icon="comments">
    Ask questions about any recorded content and get instant answers
  </Card>
</CardGroup>

## Recording a Meeting

<Steps>
  <Step title="Start Recording">
    Click the recording button in the Companion Orb, or use the keyboard shortcut `⌘⇧R` to begin recording
  </Step>

  <Step title="Select Audio Source">
    Choose your audio input:

    * **Microphone only**: Records your microphone input
    * **System audio only**: Captures audio from your Mac (meeting apps, browser, etc.)
    * **Both**: Records microphone and system audio on separate channels
  </Step>

  <Step title="Record">
    The recording runs in the background while you continue working. A subtle indicator shows that recording is active.
  </Step>

  <Step title="Stop Recording">
    Click the recording indicator or press `⌘⇧R` again to stop. EnConvo automatically begins processing.
  </Step>
</Steps>

<Tip>
  For online meetings (Zoom, Google Meet, Teams), select "System audio" or "Both" to capture all participants. For in-person meetings, "Microphone only" works best.
</Tip>

## Transcription

### Automatic Transcription

After recording, EnConvo automatically transcribes the audio using advanced speech recognition:

* **Local processing**: Transcription runs on your Mac using the Parakeet TDT model -- no audio is sent to the cloud
* **Speaker diarization**: Identifies and labels different speakers in the conversation
* **Timestamps**: Every segment includes precise timestamps for easy navigation
* **Multi-language**: Supports transcription in 20+ languages

### Transcription Output

The transcription is presented in a structured format:

```
[00:00:12] Speaker 1: Let's start with the Q3 review. Revenue
is up 15% compared to last quarter.

[00:00:28] Speaker 2: That's great. Can you break down the
growth by product line?

[00:00:35] Speaker 1: Sure. The cloud platform grew 22%,
while consulting services grew 8%.

[00:01:02] Speaker 3: What about customer retention rates?
```

### Speaker Identification

EnConvo uses voice activity detection (VAD) and speaker diarization to separate speakers:

| Feature            | Description                                                 |
| ------------------ | ----------------------------------------------------------- |
| **Auto-detection** | Automatically identifies when speakers change               |
| **Speaker labels** | Labels speakers as "Speaker 1", "Speaker 2", etc.           |
| **Custom names**   | Rename speakers to actual participant names after recording |
| **Voice profiles** | Over time, EnConvo learns to recognize recurring speakers   |

## AI Summaries

After transcription, request an AI summary to get a structured overview of the recording.

### Summary Types

| Type                 | Content                                   | Best For                            |
| -------------------- | ----------------------------------------- | ----------------------------------- |
| **Quick Summary**    | 3-5 sentence overview                     | Fast review of what was discussed   |
| **Detailed Summary** | Full structured summary with sections     | Sharing with team or archival       |
| **Action Items**     | Extracted tasks with owners and deadlines | Follow-up and task management       |
| **Key Decisions**    | Decisions made during the meeting         | Decision tracking and documentation |

### Summary Format

A typical detailed summary includes:

* **Participants**: List of speakers identified
* **Duration**: Total recording length
* **Overview**: 2-3 paragraph summary of the entire meeting
* **Topics Discussed**: Organized by topic with key points
* **Decisions Made**: Clear list of decisions with context
* **Action Items**: Tasks extracted with assigned owners and deadlines
* **Open Questions**: Unresolved topics that need follow-up

### Generating a Summary

<Steps>
  <Step title="Open Recording">
    Navigate to your recording in the recordings list
  </Step>

  <Step title="Request Summary">
    Click **Summarize** or ask "Summarize this meeting" in the chat
  </Step>

  <Step title="Choose Type">
    Select the summary type (Quick, Detailed, Action Items, or Key Decisions)
  </Step>

  <Step title="Review & Edit">
    Review the generated summary and make any corrections
  </Step>
</Steps>

## Q\&A on Recordings

One of the most powerful features is the ability to ask questions about your recordings. Instead of scrubbing through audio, simply ask:

### Example Questions

```
What did we decide about the pricing strategy?
Who is responsible for the design mockups?
What was the timeline discussed for the product launch?
Did anyone mention concerns about the budget?
Summarize what Speaker 2 said about customer feedback
What were the main disagreements in the meeting?
```

### How It Works

1. Your question is matched against the transcription using semantic search
2. Relevant segments are identified and retrieved
3. The AI synthesizes an answer based on the actual content
4. Source timestamps are provided so you can verify or listen to the original audio

<Tip>
  Q\&A works on any recording -- meetings, lectures, interviews, podcasts, or any other audio content you have recorded and transcribed.
</Tip>

## Recording Management

### Viewing Recordings

Access all your recordings through **Settings** or the Companion Orb:

* Browse recordings by date
* Search across all transcriptions
* Filter by duration, speaker count, or tags
* Preview transcriptions without opening

### Organizing Recordings

| Feature       | Description                                |
| ------------- | ------------------------------------------ |
| **Tags**      | Add custom tags to categorize recordings   |
| **Folders**   | Organize recordings into folders           |
| **Favorites** | Mark important recordings for quick access |
| **Search**    | Full-text search across all transcriptions |

### Exporting

Export recordings and transcriptions in multiple formats:

| Format              | Content                                              |
| ------------------- | ---------------------------------------------------- |
| **Audio (M4A/WAV)** | The original audio recording                         |
| **Text (.txt)**     | Plain text transcription                             |
| **Markdown (.md)**  | Formatted transcription with timestamps and speakers |
| **SRT (.srt)**      | Subtitle format for video sync                       |
| **JSON**            | Structured data with all metadata                    |

## Use Cases

<AccordionGroup>
  <Accordion title="Team Meetings" icon="users">
    Record team standups, planning sessions, and retrospectives. Generate action items automatically and share summaries with team members who could not attend.
  </Accordion>

  <Accordion title="Lectures & Courses" icon="graduation-cap">
    Record university lectures or online courses. Later, ask questions about specific topics instead of re-watching hours of content.
  </Accordion>

  <Accordion title="Client Calls" icon="phone">
    Record client meetings to capture requirements accurately. Generate summaries to share with your team and ensure nothing is lost.
  </Accordion>

  <Accordion title="Interviews" icon="user-group">
    Record job interviews or user research sessions. Review transcriptions to make fair, well-informed decisions.
  </Accordion>

  <Accordion title="Podcasts & Talks" icon="podcast">
    Record podcasts or conference talks you are listening to. Ask questions later about specific points or get summaries of the key ideas.
  </Accordion>

  <Accordion title="Personal Notes" icon="microphone">
    Use voice recording as a quick way to capture ideas and thoughts. EnConvo transcribes and organizes them for later reference.
  </Accordion>
</AccordionGroup>

## Audio Processing Technology

EnConvo uses advanced on-device audio processing:

| Technology              | Purpose                                                        |
| ----------------------- | -------------------------------------------------------------- |
| **Parakeet TDT**        | Speech-to-text transcription model optimized for Apple Silicon |
| **Silero VAD**          | Voice Activity Detection to identify speech segments           |
| **Speaker Diarization** | Identifies and separates different speakers                    |
| **Noise Reduction**     | Filters background noise for clearer transcription             |

<Note>
  All audio processing happens locally on your Mac using Apple Silicon acceleration. Your recordings and transcriptions never leave your device unless you explicitly export or share them.
</Note>

## Configuration

### Settings -> Recording

| Setting                  | Description                              | Default     |
| ------------------------ | ---------------------------------------- | ----------- |
| **Audio Source**         | Default input (mic, system, both)        | Both        |
| **Audio Quality**        | Recording quality level                  | High        |
| **Auto-transcribe**      | Transcribe automatically after recording | On          |
| **Language**             | Primary transcription language           | Auto-detect |
| **Storage Location**     | Where recordings are saved               | Default     |
| **Max Recording Length** | Maximum duration for a single recording  | Unlimited   |

### Keyboard Shortcuts

| Shortcut | Action                 |
| -------- | ---------------------- |
| `⌘⇧R`    | Start/Stop recording   |
| `⌘⇧P`    | Pause/Resume recording |

## Privacy & Security

<Warning>
  Recording meetings may have legal implications depending on your jurisdiction. Many regions require all-party consent for recording conversations. Always inform participants before recording and obtain necessary consent.
</Warning>

### Privacy Features

* All processing happens on-device -- no cloud uploads
* Recordings stored locally in encrypted storage
* No audio data is sent to AI providers
* Full control to delete recordings and transcriptions at any time

## Troubleshooting

<AccordionGroup>
  <Accordion title="No system audio captured">
    * Ensure EnConvo has audio recording permissions in System Settings -> Privacy & Security -> Screen & System Audio Recording
    * Some applications may block system audio capture
    * Try restarting the meeting application
  </Accordion>

  <Accordion title="Poor transcription quality">
    * Ensure good audio quality (minimize background noise)
    * Check that the correct language is set
    * Use an external microphone for better results
    * Speak clearly and at a moderate pace
  </Accordion>

  <Accordion title="Speaker identification issues">
    * Speaker diarization works best with clear audio separation
    * Overlapping speech is harder to separate
    * Rename speakers manually after recording for accuracy
  </Accordion>
</AccordionGroup>

## Related Features

<CardGroup cols={2}>
  <Card title="Companion Orb" icon="circle" href="/features/companion-bar">
    Quick access to recording controls
  </Card>

  <Card title="Knowledge Base" icon="database" href="/ai/knowledge-base">
    Add transcriptions to your knowledge base
  </Card>

  <Card title="Dictation" icon="microphone-lines" href="/features/dictation">
    Real-time voice-to-text input
  </Card>

  <Card title="AI Chat" icon="comments" href="/ai/chat">
    Chat with your recordings using Q\&A
  </Card>
</CardGroup>