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

# Response control

> Block keywords in agent responses and control pronunciation for voice agents.

Use response control to shape what your voice agent says and how it says it – blocking offensive language or competitor names, and fixing mispronounced terms.

<Note>
  Response control settings here apply to **voice agents**. Stop keywords run only in the voice runtime, and pronunciations only affect TTS output. For text-channel agents, these pages are safe to skip.
</Note>

<img src="https://mintcdn.com/polyai/Qu880HppNqT19Eyr/images/response-control/response-control.png?fit=max&auto=format&n=Qu880HppNqT19Eyr&q=85&s=1f663278b949aeffcb78123de03cf5cf" alt="Response controls interface" width="3006" height="1118" data-path="images/response-control/response-control.png" />

<CardGroup cols={2}>
  <Card title="Stop keywords" icon="ban" href="/response-control/stop-keywords">
    Block or log specific phrases in agent output (content moderation).
  </Card>

  <Card title="Pronunciations" icon="volume-high" href="/response-control/pronunciations">
    Control how your agent pronounces specific terms (voice tuning).
  </Card>
</CardGroup>

## Looking for translations?

Translation overrides are agent-wide (they apply to voice **and** chat), so they live alongside other multilingual settings.

<Card title="Translations" icon="language" href="/response-control/translations">
  Override auto-translated content for multilingual agents.
</Card>

## Related pages

<CardGroup cols={2}>
  <Card title="Analytics dashboard" icon="chart-line" href="/analytics/dashboards/introduction">
    View stop keyword metrics and trends.
  </Card>

  <Card title="Actions" icon="bolt" href="/managed-topics/how-to-setup-action/introduction">
    Configure actions triggered by Managed Topics.
  </Card>
</CardGroup>