# ava

> ava — iksnerd-ava. Use this tool when you need to enable on-device voice capabilities for macOS, such as dictation, text-to-speech, and live call transcription, with a secure interface that keeps all data local to the machine. It solves problems related to voice processing, transcription, and accessibility, with inputs including whisper.cpp and outputs in Kokoro format. Ideal for use cases requiring private and efficient voice processing on macOS devices.

Canonical page: https://skillsregistry.net/skills/iksnerd-ava  
JSON: https://api.skillsregistry.net/v1/skills/iksnerd-ava

## Description

On-device voice for macOS: dictation, text-to-speech, live call transcription, and an MCP server. whisper.cpp in, Kokoro out — nothing leaves the machine.

## Trust

- **Trust score (0–1):** 0.53
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/iksnerd/ava)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "iksnerd-ava"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/iksnerd-ava` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/iksnerd-ava/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt