What is the key difference between MCP Fish and Speech.sh?

MCP Fish belongs to the Text-to-Speech category with local stdio execution, while Speech.sh belongs to the Text-to-Speech category with cloud HTTP/SSE execution.

How do I install MCP Fish or Speech.sh in Claude Desktop or Cursor?

Copy the mcpServers JSON configuration snippet provided on this page into your claude_desktop_config.json or ~/.cursor/mcp.json file and restart your AI client.

Are MCP Fish and Speech.sh free or paid?

MCP Fish operates under a Free / Open Source model (No auth required). Speech.sh operates under a BYOK (Pay Provider Direct) model (API Key required).

Which MCP server has more tools and community activity?

MCP Fish lists 6 tools with 1 views and 1 GitHub stars. Speech.sh lists 6 tools with 2 views and 9 GitHub stars.

Can I use both MCP Fish and Speech.sh together in the same MCP host?

Yes! MCP hosts like Claude Desktop, Cursor, Windsurf, Cline, and VS Code support configuring multiple servers under the mcpServers object simultaneously.

Side-by-Side Model Context Protocol Comparison

MCP Fish vs Speech.sh

In-depth architectural comparison of the MCP Fish and Speech.sh MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.

At a Glance & Executive Verdict

MCP Fish

Text-to-Speech · Local stdio

Quality: 52/100 (Good) | Auth: No auth required

Speech.sh

Text-to-Speech · Remote HTTP/SSE

Quality: 39/100 (Fair) | Auth: API Key required

Verdict Summary: Choose MCP Fish if you need specialized Text-to-Speech tools running via a local process. Choose Speech.sh if your workspace requires Text-to-Speech integration with remote web transport. Both servers can be configured concurrently in your client's mcpServers manifest.

Which MCP Server Should You Choose?

Choose MCP Fish when:

You need dedicated capabilities in the Text-to-Speech domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Primary tools included: fish_generate_audio, fish_list_models, fish_get_model.

Explore MCP Fish Details

Choose Speech.sh when:

You need dedicated capabilities in the Text-to-Speech domain.
You prefer remote streaming HTTP/SSE transport architecture.
Your security boundary fits: API Key required (BYOK (Pay Provider Direct)).
You have access to required keys: OPENAI_API_KEY, SPEECH_VOICE, SPEECH_SPEED, SPEECH_MODEL, SPEECH_API_URL.
Primary tools included: Multiple voice options (troy, austin, hannah, autumn), Adjustable speech speed parameter, Hash-based caching with 24-hour auto-cleanup.

Feature & Specification Comparison

Specification	MCP Fish Text-to-Speech	Speech.sh j3k0 Text-to-Speech
Summary
Category & Scope	Text-to-Speech	Text-to-Speech
Quality signal

Tools & Capabilities Breakdown

MCP Fish Tools (6)

fish_generate_audio

Generate speech from text via a Fish voice model

fish_list_models

List available Fish voice models

fish_get_model

Fetch metadata for a specific Fish voice model

fish_get_task

Get the status / result of a generation task

fish_get_tasks_batch

Batch-fetch the status / result of multiple tasks

fish_get_usage_guide

Get the API usage guide

Ready-to-Paste Client Configurations

Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).

MCP Fish Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "mcp-fish": {
      "command": "uvx",
      "args": [
        "mcp-fish"
      ]
    }
  }
}

Speech.sh Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "j3k0-speech-sh": {
      "url": "https://api.groq.com/openai/v1/audio/speech"
    }
  }
}

Frequently Asked Questions

MCP Fish is categorized under Text-to-Speech and uses a local stdio subprocess. In contrast, Speech.sh belongs to Text-to-Speech using remote streaming HTTP/SSE transport. Select MCP Fish when you need capabilities focused on text-to-speech and Speech.sh when you require tools for text-to-speech.