Skip to main content

MCP Text-to-Speech Server for Cursor IDE (and others) with cross-platform audio playback

Project description

MCP Text-to-Speech for Cursor IDE

Add text-to-speech capabilities to Cursor IDE. Let your AI assistant speak responses, summaries, and explanations out loud.

🚀 Quick Start

Prerequisites: Cursor IDE and an OpenAI API key

Setup: Add this to your Cursor MCP settings (~/.cursor/mcp.json):

{
  "mcpServers": {
    "mcp_tts_server": {
      "command": "uvx",
      "args": ["--from", "mcp-tts", "mcp-tts-server-stdio"],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key-here",
        "PYTHONIOENCODING": "utf-8"
      }
    }
  }
}

That's it! Restart Cursor and try asking: "Can you read me a summary using text-to-speech?"

⚙️ Configuration Options

You can control the TTS system using these environment variables in your MCP config:

Variable Description Example Values Default
OPENAI_API_KEY Required - Your OpenAI API key sk-proj-abc123... -
MCP_TTS_VOICE OpenAI voice to use alloy, echo, fable, onyx, nova, shimmer, ballad ballad
MCP_TTS_VOICE_PRESET Voice style preset default, professional, calm, nyc_cabbie, chill_surfer, cheerleader, emo_teenager, eternal_optimist, dramatic default
MCP_TTS_CUSTOM_INSTRUCTIONS Custom voice instructions (overrides preset) "Speak like a pirate" -
MCP_TTS_SPEED Speech speed 0.25 to 4.0 1.0
MCP_TTS_VOLUME Playback volume 0.0 to 1.0 0.8
MCP_TTS_DEVICE_NAME Audio device name (partial match) "Speakers", "Headphones" -
MCP_TTS_DEVICE_INDEX Audio device index 0, 1, 2, etc. -

Tip: To find your audio device name, first run with basic config, then use the list_audio_devices tool to see available devices.

Voice Presets

You can use these built-in voice style presets:

  • default - Clear, friendly, and conversational
  • professional - Authoritative business voice
  • calm - Composed, reassuring with quiet authority
  • nyc_cabbie - Fast-talking New Yorker with edge
  • chill_surfer - Laid-back, mellow, effortlessly cool
  • cheerleader - High-energy, enthusiastic, motivational
  • emo_teenager - Sarcastic, disinterested, melancholic
  • eternal_optimist - Positive, solution-oriented
  • dramatic - Low, hushed, suspenseful with theatrical flair

🎵 Usage Examples

  • "Use text-to-speech to explain this code"
  • "Read me the changes you just made"
  • "List my audio devices"
  • "Switch to a professional voice style"

📚 Full Documentation

For advanced configuration, voice presets, troubleshooting, and development setup, see SETUP_GUIDE.md.


Status: ✅ Working with Cursor IDE • 🎵 7 TTS tools available • 🔊 Cross-platform audio

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_tts-0.2.6.tar.gz (34.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_tts-0.2.6-py3-none-any.whl (32.6 kB view details)

Uploaded Python 3

File details

Details for the file mcp_tts-0.2.6.tar.gz.

File metadata

  • Download URL: mcp_tts-0.2.6.tar.gz
  • Upload date:
  • Size: 34.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.13

File hashes

Hashes for mcp_tts-0.2.6.tar.gz
Algorithm Hash digest
SHA256 6c302a0a436744491317f25565d2c8c70786642e4561d264c2bfebf48952a232
MD5 e7edb042d2c4dbf780e1135c6b3db034
BLAKE2b-256 5f2aa40a5d0c6934b4479d93380fed63654b05071272a63bf6787ccadcfa1744

See more details on using hashes here.

File details

Details for the file mcp_tts-0.2.6-py3-none-any.whl.

File metadata

  • Download URL: mcp_tts-0.2.6-py3-none-any.whl
  • Upload date:
  • Size: 32.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.13

File hashes

Hashes for mcp_tts-0.2.6-py3-none-any.whl
Algorithm Hash digest
SHA256 2f7c8e9e01eba4cacea37842575896cba6b96f4f798dc55a4c5d09a79488504b
MD5 57df4ad9a2bcb6111245f63607409c40
BLAKE2b-256 f498168d20711fed6a8de98c08d3a2b773c270d25b83caf2419124a69e2e9884

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page