1. Conduid
  2. Commerce
  3. j3k0/speech.sh
MCP server · Commerce

j3k0/speech.sh

by · github.com/j3k0/speech.sh

Simple curl script to play aloud what you type, useful if your voice is suddenly broken.

Unclaimed GPL-3.0 last commit 7 months ago commerce
InstallView source
47Fair

Scored 18 hours ago · breakdown

About j3k0/speech.sh

j3k0/speech.sh is an MCP server published by j3k0 in the Commerce category: simple curl script to play aloud what you type, useful if your voice is suddenly broken.

The repository has 9 stars and 4 forks, with the last commit 7 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/j3k0/speech.sh

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about j3k0/speech.sh

Powered by Claude · Grounded in docs

I know everything about j3k0/speech.sh. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 18 hours ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • ✓License declaredUsable under a stated license.
  • !Tests presentNo tests found. Behaviour changes may go unnoticed between versions.
  • !Dependencies pinnedNo lockfile. Installs can pull different code over time.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README

Speech.sh

A text-to-speech CLI and MCP server using the Groq TTS API (OpenAI-compatible).

Features

  • Convert text to speech with a simple command
  • Multiple voice options (troy, austin, hannah, autumn)
  • Adjustable speech speed
  • Hash-based caching to avoid duplicate API calls (24h auto-cleanup)
  • Retry with exponential backoff
  • Audio playback via ffplay, mplayer, or VLC
  • MCP server for integration with AI assistants (Claude Desktop, Claude Code)

Quick Start

git clone https://github.com/j3k0/speech.sh.git
cd speech.sh
export OPENAI_API_KEY="your-groq-api-key"
./speech.sh --text "Hello, world!"

Dependencies

  • curl, jq (for the shell version)
  • One audio player: ffplay (from ffmpeg), mplayer, or vlc

CLI Usage

# Basic
./speech.sh --text "Hello, world!"

# With options
./speech.sh --text "Hello!" --voice austin --speed 1.2 --verbose

Options

-t, --text TEXT       Text to convert to speech (required)
-v, --voice VOICE     Voice to use (default: troy)
-s, --speed SPEED     Speech speed (default: 1.0)
-o, --output FILE     Output file path (default: auto-generated)
-a, --api_key KEY     API key
-m, --model MODEL     TTS model (default: canopylabs/orpheus-v1-english)
-p, --player PLAYER   Audio player: auto, ffmpeg, mplayer, vlc (default: auto)
-r, --retries N       Retry attempts (default: 3)
-T, --timeout N       Timeout in seconds (default: 30)
    --verbose         Enable verbose logging

API Key

Provide your Groq API key in one of three ways (in order of precedence):

  1. --api_key "your-key"
  2. export OPENAI_API_KEY="your-key"
  3. A file named API_KEY in the script's directory

MCP Server

Two implementations are available:

Python (recommended)

Uses the FastMCP SDK. Requires Python 3.10+ and uv.

# Setup
uv venv --python python3 .venv
uv pip install --python .venv/bin/python "mcp[cli]" httpx

# Run
OPENAI_API_KEY="your-key" .venv/bin/python server.py

Claude Desktop / Claude Code configuration

{
  "mcpServers": {
    "speak": {
      "command": "/path/to/speech.sh/.venv/bin/python",
      "args": ["/path/to/speech.sh/server.py"],
      "env": {
        "OPENAI_API_KEY": "your-groq-api-key",
        "SPEECH_VOICE": "troy",
        "SPEECH_SPEED": "1.0",
        "SPEECH_MODEL": "canopylabs/orpheus-v1-english"
      }
    }
  }
}

Shell (legacy)

The original shell-based MCP server (mcp.sh). Works in environments without Python but may hit macOS sandboxing issues with Claude Desktop.

./mcp.sh

MCP Tool

The server exposes a single speak tool:

Parameter Type Required Default Description
text string yes The text to speak
voice string no troy Voice to use
speed number no 1.0 Speech speed

Environment Variables

Variable Description Default
OPENAI_API_KEY Groq API key (required)
SPEECH_VOICE Default voice troy
SPEECH_SPEED Default speed 1.0
SPEECH_MODEL TTS model canopylabs/orpheus-v1-english
SPEECH_API_URL API endpoint (Python) https://api.groq.com/openai/v1/audio/speech

Architecture

  • speech.sh - Shell-based TTS engine (API calls, caching, playback)
  • mcp.sh - Shell-based MCP wrapper over speech.sh (JSON-RPC 2.0 over stdio)
  • server.py - Python MCP server, self-contained replacement for both scripts above

License

GPL

README fetched from the repository 18 hours ago. The original is authoritative.

Questions

About j3k0/speech.sh

How do I install j3k0/speech.sh?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is j3k0/speech.sh safe to use with an AI agent?

Its trust score is 47 out of 100 (fair). It passes 3 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is j3k0/speech.sh still maintained?

The last commit was 7 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.