DAISYS MCP

Name: DAISYS MCP
Author: DAISYS

by DAISYS

High-quality text-to-speech and voice generation through AI assistants

ai-ml Node.js Beginner Self-hostable

⭐ 50 stars 📅 Updated: 1mo ago

View on GitHub View package

Description

MCP server for the DAISYS text-to-speech platform that enables AI assistants to generate natural-sounding voice outputs. Supports multiple voices, languages, and speaking styles for creating voiceovers, narrations, and audio content programmatically. Integrates DAISYS's neural TTS engine into your development workflow, letting you generate speech files, preview different voices, and fine-tune voice parameters — all through natural language commands from your AI assistant. Ideal for content creators, app developers, and anyone who needs to produce professional audio content at scale.

✅ Best for

Developers and content creators who need to generate professional voice content from AI assistants

⏭️ Skip if

You need real-time voice streaming or voice cloning capabilities

💡 Use cases

Generating voiceovers and narrations for video or podcast content
Prototyping voice interfaces and audio experiences
Creating multilingual audio content with different voice styles
Batch-generating speech files for applications and presentations

👍 Pros

✓ High-quality neural TTS with natural-sounding output
✓ Multiple voices, languages, and speaking styles available
✓ Simple integration via npx with API key setup
✓ Programmatic audio generation saves time over manual recording

👎 Cons

✗ Requires a DAISYS API key and account
✗ Voice quality and variety depend on DAISYS's available models
✗ Generated audio files need separate hosting or delivery solution

🔧 Exposed tools (4 tools)

Tool	Category	Description
list_voices	configuration	List available voices, languages, and speaking styles
configure_voice	configuration	Configure voice parameters like speed, pitch, and emotion
generate_speech	generation	Generate speech audio from text with selected voice and style
generate_audio_file	generation	Generate and export a speech audio file in various formats

⚡ Installation

Prerequisites:

• Node.js v18+
• DAISYS API key
• API key required

Check Claude Code documentation to configure this MCP server.

💡 Tips & tricks

Use list_voices first to explore available voices and styles before generating speech. Experiment with different voice configurations to find the best match for your content type.

🔄 Alternatives

Audio MCP Server

Audio recording, playback, and text-to-speech through AI assistants

Similar functionality

Mureka MCP

AI-powered music generation — create lyrics, songs, and instrumentals from your editor