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

# Agent settings

> Configuring the behaviour and voice of a HubTalk AI v4 agent: where to start and where everything lives.

# Agent settings

Agent settings are available in the **Settings** tab of the agent builder. Open an agent, select **Settings**, and configure the options that control conversation handling, the agent's speech, knowledge base usage, and call control.

There are a lot of them, so they are split across separate pages — listed below. Only what has to be decided first stays here.

## Pipeline mode

Choose how the agent processes conversations:

* **STT-LLM-TTS pipeline** — configure separate speech-to-text, language model, and text-to-speech options.
* **Realtime model** — use a real-time speech-to-speech model for the voice agent.

<img src="https://mintcdn.com/hubtalk/yYJS_d_pzapQzHCp/images/v4_settings_pipeline_mode_en.png?fit=max&auto=format&n=yYJS_d_pzapQzHCp&q=85&s=d44224ddce057800bff8e17f4979c01b" alt="Pipeline mode toggle: STT-LLM-TTS or Realtime model" width="1440" height="900" data-path="images/v4_settings_pipeline_mode_en.png" />

<Warning>
  **Decide this before the rest: some settings do not work in realtime mode.** Such an agent has no separate synthesis step and does not fill fields as the conversation goes, so [conversation goals](/v4/platform/agent-settings/goals), [phrase corrections and pause markup](/v4/platform/agent-settings/speech-corrections) have no effect. The toggles still switch on but do nothing — wherever that is the case, the page says so plainly.
</Warning>

## Where each setting lives

<CardGroup cols={2}>
  <Card title="Prompt, models and knowledge" icon="brain" href="/v4/platform/agent-settings/prompt-and-models">
    The global prompt and variable substitution in authored text, execution and classifier models, service tier, cache warm-up, knowledge bases, flex mode.
  </Card>

  <Card title="Voice: STT, TTS and VAD" icon="microphone" href="/v4/platform/agent-settings/voice">
    Speech recognition and synthesis, speech detection and interruptions, background audio, turn language detection, the pre-TTS normalizer.
  </Card>

  <Card title="Phrase corrections and pauses" icon="comment-dots" href="/v4/platform/agent-settings/speech-corrections">
    The organization's replacement dictionary and `[pause N]` markup: how the agent sounds when it reads numbers and amounts.
  </Card>

  <Card title="Recording and call control" icon="phone" href="/v4/platform/agent-settings/call-control">
    Call recording and its retention, the duration cap, silence reminders, the transfer failure message.
  </Card>

  <Card title="Conversation goals" icon="list-check" href="/v4/platform/agent-settings/goals">
    What has to be established in a conversation, how the platform marks it done, and what the mechanism deliberately does not do.
  </Card>

  <Card title="Analytics, observers and webhooks" icon="chart-simple" href="/v4/platform/agent-settings/analytics">
    Post-call analysis and custom fields, observers with their reactions, post-call webhooks.
  </Card>
</CardGroup>