# Ezkielyna Audio

> Ezkielyna Audio is a paid MCP server for design and media. Text to speech and transcription from local audio files, including Indonesian. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** CLI, API
- **Repository:** https://github.com/ezkielynagroup/ezkielyna-audio-mcp
- **MCP Registry name:** io.github.EzkielynaGroup/ezkielyna-audio-mcp
- **Categories:** [design and media](https://ai-powered.com/categories/design-and-media), [AI models and LLM tooling](https://ai-powered.com/categories/ai-and-llm)
- **Listing updated:** 2026-11-18

## About

Speech output is written to a folder on your machine (default ~/Music/Ezkielyna) as MP3 or WAV, and existing files are never overwritten. Transcription reads a local file up to 25 MB in formats such as mp3, m4a, ogg and flac, and can return plain text, SRT or VTT subtitles. A third tool lists the audio models with prices, voices and which ones your key can use.

The default voice for the edge-tts model is id-ID-GadisNeural, an Indonesian female voice, with an Indonesian male option available. Other models bring voices such as Kore or eve. Text per call is capped at 4,000 characters.

Calls go through the Ezkielyna API with a prepaid key, so cost is per input character for speech and by audio length for transcription. A per-session cap on paid calls (default 30) guards against runaway loops, and the key is never printed.

## Features

- **Text to speech:** Converts up to 4,000 characters to an MP3 or WAV file in a chosen voice.
- **Local transcription:** Transcribes local audio and can return text, SRT or VTT.
- **Model and price list:** Shows models, voices, formats and per-model price, marking those your key can use.
- **Session call cap:** Limits paid calls per session, default 30.
- **No overwrites:** New audio is saved under fresh names inside one output folder.

## Good for

- Transcribe an Indonesian voice note and summarise it
- Read a product description aloud and save it as a file
- Generate SRT subtitles from a recording
- Compare speech models and prices before choosing one

## Install

### Claude Code (Terminal)

```sh
claude mcp add ezkielyna-audio-mcp --env EZKIELYNA_API_KEY='<EZKIELYNA_API_KEY>' -- npx -y ezkielyna-audio-mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "ezkielyna-audio-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ezkielyna-audio-mcp"
      ],
      "env": {
        "EZKIELYNA_API_KEY": "<EZKIELYNA_API_KEY>"
      }
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "ezkielyna-audio-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ezkielyna-audio-mcp"
      ],
      "env": {
        "EZKIELYNA_API_KEY": "<EZKIELYNA_API_KEY>"
      }
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "ezkielyna-audio-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "ezkielyna-audio-mcp"
      ],
      "env": {
        "EZKIELYNA_API_KEY": "<EZKIELYNA_API_KEY>"
      }
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "ezkielyna-audio-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ezkielyna-audio-mcp"
      ],
      "env": {
        "EZKIELYNA_API_KEY": "<EZKIELYNA_API_KEY>"
      }
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "ezkielyna-audio-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ezkielyna-audio-mcp"
      ],
      "env": {
        "EZKIELYNA_API_KEY": "<EZKIELYNA_API_KEY>"
      }
    }
  }
}
```

## Tools

- `text_to_speech`: Converts text of up to 4,000 characters to speech saved as MP3 or WAV.
- `transcribe_audio`: Transcribes a local audio file to text, SRT or VTT.
- `list_audio_models`: Lists text-to-speech and speech-to-text models with price, groups, voices and formats.

## FAQ

### What key do I need?

An Ezkielyna API key whose group includes audio models; the Auto group is the simplest choice.

### Which formats can it transcribe?

mp3, m4a, mp4, wav, ogg, oga, opus, webm, flac, aac, mpga and mpeg, up to 25 MB.

### What is the default speech model?

edge-tts, which only returns MP3.

### How much does it cost?

Credit is prepaid from $0.5; edge-tts is listed at $1 per million characters.

### Is Ezkielyna Audio free?

No. Ezkielyna Audio is a paid product.

### How do I add Ezkielyna Audio to Claude Code?

Run this command in your terminal: claude mcp add ezkielyna-audio-mcp --env EZKIELYNA_API_KEY='<EZKIELYNA_API_KEY>' -- npx -y ezkielyna-audio-mcp

### What are the best alternatives to Ezkielyna Audio?

The closest alternatives to Ezkielyna Audio are HyperFrames by HeyGen, headroom, omniget, next-ai-draw-io and mcp-for-blender.

## Where this comes from

- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [HyperFrames by HeyGen](https://ai-powered.com/mcp/hyperframes-by-heygen): HyperFrames by HeyGen is a freemium MCP server for design and media.
- [headroom](https://ai-powered.com/mcp/headroom-3): headroom is an open-source MCP server for ai models and llm tooling.
- [omniget](https://ai-powered.com/mcp/omniget): omniget is an open-source MCP server for ai models and llm tooling.
- [next-ai-draw-io](https://ai-powered.com/mcp/next-ai-draw-io-2): next-ai-draw-io is an open-source MCP server for ai models and llm tooling.
- [mcp-for-blender](https://ai-powered.com/mcp/mcp-for-blender): mcp-for-blender is an open-source MCP server for design and media.
- [ffmpeg-skill](https://ai-powered.com/mcp/ffmpeg-skill): ffmpeg-skill is an open-source MCP server for design and media.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [unity-mcp](https://ai-powered.com/mcp/unity-mcp-2): unity-mcp is an open-source MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/ezkielyna-audio
