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

# Conversation Dynamics

> Conversation Dynamics control the timing and behavior of your voice assistant during real-time interactions. These settings determine how quickly the assistant responds, how long it waits for user input, and how deeply it reasons about responses.

## Why Dynamics Matter

Natural conversation requires careful timing. Respond too quickly and you interrupt users mid-thought. Wait too long and the conversation feels awkward. Voxworks provides fine-grained control over these dynamics to create natural, human-like interactions.

***

## Key Settings

| Setting                | What It Controls                                             | Options                                       |
| ---------------------- | ------------------------------------------------------------ | --------------------------------------------- |
| **Response Eagerness** | How quickly the assistant responds after user stops speaking | keen, normal, patient                         |
| **Thinking Effort**    | How deeply the LLM reasons about responses                   | fast, normal, deep                            |
| **Silence Tolerance**  | How long to wait before prompting idle users                 | hurried, patient, extremely patient, infinite |
| **Keywords**           | Terms to improve transcription accuracy                      | Custom word list                              |

***

## How Dynamics Work Together

During a conversation turn:

1. **User speaks** — Voice activity detection (VAD) detects speech
2. **User pauses** — System starts the eagerness timer
3. **Eagerness applied** — Timer duration based on eagerness setting
4. **Turn completion check** — AI assesses whether the user has finished their thought
5. **Response generated** — LLM generates response with configured thinking effort
6. **Assistant speaks** — Once the eagerness timer has expired, the Text-to-speech delivers the assistant response
7. **Idle monitoring** — If user doesn't respond, silence tolerance kicks in

***

## Finding the Right Balance

The goal is natural conversation flow:

| Too Fast            | Just Right             | Too Slow           |
| ------------------- | ---------------------- | ------------------ |
| Interrupts users    | Natural back-and-forth | Awkward pauses     |
| Feels rushed        | Comfortable pace       | Seems unresponsive |
| Misses context      | Complete understanding | Over-thinking      |
| Incorrect responses | Correct responses      | Seems unresponsive |

Start with default settings and adjust based on testing with real conversations. See the individual setting pages for detailed guidance:

* [Response Eagerness](/conversation-dynamics/response-eagerness) — Adjust how quickly the assistant responds after the user stops speaking
* [Thinking Effort](/conversation-dynamics/thinking-effort) — Control the depth of reasoning for more accurate or faster responses
* [Silence Tolerance](/conversation-dynamics/silence-tolerance) — Configure how long the assistant waits before prompting idle users

***

## Per-Step Configuration

Each step in your flow can have its own dynamics settings:

```text theme={null}
Step: Complex questions that require thoughtful consideration from both user and assistant
  - Eagerness: patient (wait for complete thoughts)
  - Thinking Effort: deep (deeper reasoning)
  - Silence Tolerance: patient

Step: Simple confirmation
  - Eagerness: keen (quick yes/no expected)
  - Thinking Effort: fast (straightforward response)
  - Silence Tolerance: hurried
```

***

## Next Steps

* [Assistant Behaviour](/conversation-dynamics/assistant-behaviour) — Understand behavioural limitations and what you can influence
* [Keywords](/conversation-dynamics/keywords) — Improve transcription accuracy for specific terms
* [Silence Tolerance](/conversation-dynamics/silence-tolerance) — Handle idle users
* [Response Eagerness](/conversation-dynamics/response-eagerness) — Control response timing
* [Thinking Effort](/conversation-dynamics/thinking-effort) — Adjust reasoning depth