Kokoro Text-to-Speech Server

MCPOpen SourceApache-2.054.0

by mberg • Documentation & Docs

A self-hosted MCP server that converts text to MP3 using the Kokoro TTS model with optional S3 upload and local file management.

Example Use Cases

1
Produce spoken audio from text on-demand and store output as MP3 files locally or in S3.
2
Configurable voice, speed, and language options for TTS to personalize responses or notifications.
3
An on-premises or self-hosted TTS solution with file retention and automatic cleanup policies.

Description

This MCP server runs the Kokoro TTS model (ONNX/voices files) to generate .mp3 audio from provided text and can optionally upload results to S3. It includes a client script for sending requests, configurable defaults for voice/speed/language, and environment-driven settings for S3, storage location, and automatic cleanup. The server is designed for local or networked deployment (UV runner recommended) so you can integrate TTS into pipelines or agents without relying on external hosted services.

Quick Actions

View on GitHub

Security

Scanned 3 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

D44/100

4/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFree

Capabilities0 Tools / 0 Prompts / 0 Resources

Ownermberg

CategoryDocumentation & Docs

DependenciesStandalone