> For the complete documentation index, see [llms.txt](https://cogna8-io.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://cogna8-io.gitbook.io/docs/product-interface/voice.md).

# Voice

Cogna8 supports voice interaction through speech-to-text input and text-to-speech output. The same state extraction, conflict detection, and action gating apply regardless of whether input arrives via typing or voice.

***

## Voice Input (Speech-to-Text)

Speak naturally and the system transcribes your input for processing through the standard integrity pipeline.

## Voice Output (Text-to-Speech)

System responses and integrity feedback can be read aloud. Configure voice selection and playback behavior in General Settings.

{% hint style="warning" %}
**If voice transcription quality is poor, downstream state may be inaccurate.** Inspect the captured text message and use State and Why to verify what the system actually formed.
{% endhint %}