Typecast API
An MCP server for the Typecast API, enabling AI-powered voice generation for various content.
typecast-api-mcp-server
MCP Server for typecast-api, enabling seamless integration with MCP clients. This project provides a standardized way to interact with Typecast API through the Model Context Protocol.
About
This project implements a Model Context Protocol server for Typecast API, allowing MCP clients to interact with the Typecast API in a standardized way.
Supported Models
| Model | Description | Emotion Control |
|---|---|---|
| ssfm-v30 | Latest model (recommended) | Preset + Smart Mode |
| ssfm-v21 | Stable production model | Preset only |
ssfm-v30 Features
- 7 Emotion Presets: normal, happy, sad, angry, whisper, toneup, tonedown
- Smart Mode: AI automatically infers emotion from context using
previous_textandnext_text - 37 Languages: Extended language support
Feature Implementation Status
| Feature | Status |
|---|---|
| Voice Management | |
| Get Voices (V2 API) | ✅ |
| Get Voice (V2 API) | ✅ |
| Text to Speech | ✅ |
| Play Audio | ✅ |
| ssfm-v30 Support | |
| Preset Mode | ✅ |
| Smart Mode | ✅ |
Setup
Environment Variables
Set the following environment variables:
TYPECAST_API_KEY=<your-api-key>
TYPECAST_OUTPUT_DIR=<your-output-directory> # default: ~/Downloads/typecast_output
Usage with Claude Desktop / Cursor
You can add the following to your claude_desktop_config.json or Cursor MCP settings:
Recommended: Using uvx (No installation required)
{
"mcpServers": {
"typecast-api-mcp-server": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/neosapience/typecast-api-mcp-server.git",
"typecast-api-mcp-server"
],
"env": {
"TYPECAST_API_KEY": "YOUR_API_KEY",
"TYPECAST_OUTPUT_DIR": "PATH/TO/YOUR/OUTPUT/DIR"
}
}
}
}
This method automatically fetches and runs the server from GitHub without manual cloning.
Note for Linux users: If you're running on Linux, you need to add the XDG_RUNTIME_DIR environment variable to the env section:
"env": {
"TYPECAST_API_KEY": "YOUR_API_KEY",
"TYPECAST_OUTPUT_DIR": "PATH/TO/YOUR/OUTPUT/DIR",
"XDG_RUNTIME_DIR": "/run/user/1000"
}
Alternative: Local Installation
If you prefer to clone and run locally:
Git Clone
git clone https://github.com/neosapience/typecast-api-mcp-server.git
cd typecast-api-mcp-server
Dependencies
This project requires Python 3.10 or higher and uses uv for package management.
# Create virtual environment and install packages
uv venv
uv pip install -e .
Local Configuration
{
"mcpServers": {
"typecast-api-mcp-server": {
"command": "uv",
"args": [
"--directory",
"/PATH/TO/YOUR/PROJECT",
"run",
"typecast-api-mcp-server"
],
"env": {
"TYPECAST_API_KEY": "YOUR_API_KEY",
"TYPECAST_OUTPUT_DIR": "PATH/TO/YOUR/OUTPUT/DIR"
}
}
}
}
Replace /PATH/TO/YOUR/PROJECT with the actual path where your project is located.
Manual Execution
You can also run the server manually:
uv run python app/main.py
Contributing
Contributions are always welcome! Feel free to submit a Pull Request.
License
MIT License
Máy chủ liên quan
Spotify MCP Node Server
Control Spotify playback and manage playlists using AI assistants and IDEs.
SmartThings
Integrate and control SmartThings devices using a personal access token.
PayPal Account Updater Subscription Connector
Integrates with PayPal's Account Updater service to maintain fresh payment card information in e-commerce systems.
Vanta MCP Server
A server for interacting with Vanta's security compliance platform.
Remote MCP Server (Authless)
A remote MCP server deployable on Cloudflare Workers without authentication.
Whop MCP
Whop provides Model Context Protocol (MCP) servers to manage your servers and accelerate app development with AI assistance.
Remote MCP Server (Authless)
An authentication-free remote MCP server deployable on Cloudflare Workers or locally via npm.
Coolify MCP Server
An MCP server for interacting with the Coolify API to manage servers and applications.
HashiCorp Vault
Securely manage secrets and policies in HashiCorp Vault through an MCP interface.
Octodet Keycloak
Administer Keycloak by managing users, realms, roles, and other resources through an LLM interface.