Back to MCP Servers
Kokoro Text to Speech MCP Server

Kokoro Text to Speech MCP Server

Public
mberg/kokoro-tts-mcp

Generates high-quality MP3 text-to-speech audio with customizable voice, speed, and language options, supporting local storage and optional AWS S3 upload for scalable Model Context Protocol (MCP) applications.

python
0 tools
May 30, 2025
Updated Jun 4, 2025

Supercharge Your AI with Kokoro Text to Speech MCP Server

MCP Server

Unlock the full potential of Kokoro Text to Speech MCP Server through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.

Unified API Access
Complete Tracing
Instant Setup
Get Started Now

Free tier available • No credit card required

Instant Setup
99.9% Uptime
10,000+Monthly Requests
Configuration Requirements
none
Configure authentication and required variables to access this MCP server
Required Environment Variables
AWS_ACCESS_KEY_ID
Optional
string

Your AWS access key ID

AWS_S3_BUCKET_NAME
Optional
string

S3 bucket name

AWS_SECRET_ACCESS_KEY
Optional
string

Your AWS secret access key

MCP_CLIENT_HOST
Optional
string

Hostname for client connections to the server

Default: localhost
S3_ENABLED
Optional
string

Enable S3 uploads (set to "true" or "1")

Default: true
MCP_PORT
Optional
string

Port to listen on

Default: 9876
TTS_SPEED
Optional
string

Default speed for the TTS client

Default: 1.0
TTS_VOICE
Optional
string

Default voice for the TTS client

Default: af_heart
MP3_FOLDER
Optional
string

Path to store MP3 files (default is 'mp3' folder in script directory)

AWS_REGION
Optional
string

S3 region (e.g., us-east-1)

Default: us-east-1
AWS_S3_FOLDER
Optional
string

Folder path within the S3 bucket

Default: mp3
MCP_HOST
Optional
string

Host to bind the server to

Default: 0.0.0.0
AWS_S3_ENDPOINT_URL
Optional
string

Optional custom endpoint URL for S3-compatible storage

DEBUG
Optional
string

Enable debug mode (set to "true" or "1")

MP3_RETENTION_DAYS
Optional
string

Number of days to keep MP3 files before automatic deletion

DELETE_LOCAL_AFTER_S3_UPLOAD
Optional
string

Whether to delete local MP3 files after successful S3 upload (set to "true" or "1")

TTS_LANGUAGE
Optional
string

Default language for the TTS client

Default: en-us

Security Notice

Your environment variables and credentials are securely stored and encrypted. LangDB never shares these configuration values with third parties.

Related MCPs5
  • Speech MCP Server
    Speech MCP Server

    Provides high-quality text-to-speech conversion with customizable voice and speed options via a Model Context Protocol (MCP) compliant interface using the Kokoro TTS model.

    Added May 30, 2025
  • Kokoro TTS MCP Server
    Kokoro TTS MCP Server

    Provides text-to-speech synthesis via Model Context Protocol with customizable voices, adjustable speech speed, cross-platform audio playback, and options for saving or playing audio files.

    Added May 30, 2025
  • MCP Video Audio Text Extraction Server
    MCP Video Audio Text Extraction Server

    Provides standardized Model Context Protocol access to extract and transcribe text from videos and audio across major platforms using OpenAI's Whisper for high-quality, multi-language speech recognition.

    Added May 30, 2025
  • Audio Transcriber MCP Server
    Audio Transcriber MCP Server

    Provides audio transcription capabilities using OpenAI's API within a Model Context Protocol (MCP) server, supporting customizable language options and file-saving features for seamless speech-to-text conversion.

    1 tools
    Added May 29, 2025
  • ElevenLabs Text-to-Speech MCP
    ElevenLabs Text-to-Speech MCP

    Integrates ElevenLabs Text-to-Speech with Cursor via Model Context Protocol, offering voice selection, real-time WebSocket communication, and a modern React frontend for seamless text-to-speech conversion.

    Added May 30, 2025