# Voice Agent

> Local Voice Input/Output for Agents using the AI Voice Agent API.

- Skill: `kbarbel640-del/voice-agent` (Agent Skill, multi-file: 5 files)
- Install (CLI): `npx skillmds@latest add kbarbel640-del/voice-agent`
- Raw SKILL.md: https://api.skillmd.com/api/skills/kbarbel640-del/voice-agent/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: kbarbel640-del (https://skillmd.com/u/kbarbel640-del)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/kbarbel640-del/voice-agent

---


# Voice Agent

This skill allows you to speak and listen to the user using the local Voice Agent API.

## Behavior Guidelines
-   **Audio First**: When the user communicates via audio (files), your PRIMARY mode of response is **Audio File**.
-   **Silent Delivery**: When sending an audio response, **DO NOT** send a text explanation like "I sent an audio". Just send the audio file.
-   **Workflow**:
    1.  User sends audio.
    2.  You usage `transcribe` to read it.
    3.  You think of a response.
    4.  You usage `synthesize` to generate the audio file.
    5.  You send the file.
    6.  **STOP**. Do not add text commentary.

## Tools

### Transcribe File
To transcribe an audio file (Speech-to-Text), run the client script with the `transcribe` command.

```bash
python3 {baseDir}/scripts/client.py transcribe "/path/to/audio/file.ogg"
```

### Synthesize to File
To generate audio from text and save it to a file (Text-to-Speech), run the client script with the `synthesize` command.

```bash
python3 {baseDir}/scripts/client.py synthesize "Text to speak" --output "/path/to/output.mp3"
```

### Health Check
To check if the voice agent API is running and healthy:

```bash
python3 {baseDir}/scripts/client.py health
```

### Service Management
If the `Health Check` fails or you receive a connection error, the service may be stopped.
You can attempt to start it by running:

```bash
{baseDir}/scripts/start.sh
```