> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://developers.alephant.io/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://developers.alephant.io/_mcp/server.

# Voice

> Configure voice input or output while controlling audio data, models, and user authorization.

Voice capabilities may support speech-to-text, text-to-speech, or related conversation experiences. Before enabling them, confirm audio processing, retention, and egress policies.

## Capability Boundary

| Area               | Guidance                                                                       |
| ------------------ | ------------------------------------------------------------------------------ |
| Data Handling      | Define whether audio is uploaded externally, stored, and retained.             |
| Model Service      | Use approved voice models or services.                                         |
| User Authorization | Show clear notices for audio that may include personal or meeting information. |
| Audit              | Record call status, errors, and associated requests.                           |

## Before Configuration

* Confirm voice-service credentials, models, and language support.
* Define the users, groups, and scenarios allowed to use voice.
* Check privacy, compliance, and meeting-recording requirements.

## Verification

* Test recognition or synthesis with low-risk audio.
* Confirm unauthorized users cannot use the capability.
* Check user-facing messages for failures, timeouts, or unsupported languages.