# Giggy Speech MCP

Giggy Speech MCP is an MCP server for Claude Code that exposes Giggy voice generation and recorded-audio transcription. Agents can look up voices, create speech, and retrieve transcripts.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: giggy-ai
- License: ISC · policy=link-only · description only; the file stays with the author
- Source: https://github.com/giggy-ai/giggy-mcp
- Updated: 2026-11-04
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/giggy-speech-mcp

## What it does

The server gives an agent access to Giggy tools for browsing available voices, generating spoken audio, and transcribing recordings. Transcription runs asynchronously; the completed text is retrieved separately using the generation UUID.

It connects over Streamable HTTP to `https://giggy.ai/mcp`. Requests need a Giggy API key supplied through the `GIGGY_API_KEY` environment variable. The MCP endpoint handles recordings, not live microphone audio.

## Requirements
- Remote server: `https://giggy.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http giggy-speech-mcp https://giggy.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add giggy-speech-mcp --url https://giggy.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "giggy-speech-mcp": {
            "url": "https://giggy.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "giggy-speech-mcp": {
            "type": "http",
            "url": "https://giggy.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http giggy-speech-mcp https://giggy.ai/mcp
```

## When to use it
- browse Giggy's available voices
- generate spoken audio from text
- transcribe a recorded audio file
- retrieve a completed result by generation UUID

## Example prompts
- Show me the available Giggy voices and create a short sample with one of them.
- Transcribe this recording and return the text once processing finishes.
- Fetch the completed result for this generation UUID.

## Similar
- [azure-speech](https://affpapa.org/en/nevibecode/skills/calesthio-azure-speech.md) — skill · 132 installs
- [speech](https://affpapa.org/en/nevibecode/skills/speech.md) — skill · 3900 installs
- [azure-text-to-speech](https://affpapa.org/en/nevibecode/skills/azure-text-to-speech.md) — skill · 738 installs
- [Text to Speech — 20+ Languages, MP3 Output](https://affpapa.org/en/nevibecode/mcp/text-to-speech-20-languages-mp3-output.md) — MCP server · 2769 installs
- [text-to-speech](https://affpapa.org/en/nevibecode/skills/text-to-speech.md) — skill · 22900 installs
- [speech-engine](https://affpapa.org/en/nevibecode/skills/speech-engine.md) — skill · 9800 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
