Install Edge-TTS MCP Server

Pick your client, copy the command, done.

Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.

Run this once before adding it to Claude Code.

pip install -r requirements.txt

claude mcp add -e "PYTHONPATH=${PYTHONPATH}" edge-tts -- python /path/to/edge-tts/main.py

Replace any placeholder paths in the command with the real path on your machine.

Required:PYTHONPATH

Environment Variables

Set these before running Edge-TTS MCP Server.

VariableDescriptionRequired

PYTHONPATHPath to the source directory to ensure Python can find the modules.Yes

Once configured, Edge-TTS MCP Server gives your AI agent access to:

text_to_speechConvert text into speech audio.

textvoiceratevolumepitchboundaryformat

list_voicesQuery available voices with filtering options.

localegendername_pattern

save_audioSave audio data to a file.

audio_datafilenameformat

get_voice_infoGet detailed information about a specific voice.

voice_name

generate_subtitlesGenerate subtitle files for speech.

textvoicesubtitle_formatboundary_type

After setup, try these prompts with your AI agent:

→List all available Chinese voices for text-to-speech.

→Convert the following text to an audio file using the zh-CN-XiaoxiaoNeural voice: 'Hello, welcome to the MCP server.'

→Generate an SRT subtitle file for the text 'This is a test of the text to speech system.'

→Get detailed information about the voice en-US-JennyNeural.

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Python 3.8+ with pip installed
PYTHONPATH — Path to the source directory to ensure Python can find the modules.

Save the docs, env vars, and workflow around Edge-TTS MCP Server in Conare so Claude Code, Codex, and Cursor remember it next time.