Text-to-speech, AI voiceover, voice cloning and SRT/VTT subtitles for AI agents.
TTS MCP Server is an MCP integration. Text-to-speech, AI voiceover, voice cloning and SRT/VTT subtitles for AI agents.
The published pypi package is tts-mcp-server, version 0.1.1. Its declared MCP transport is stdio.
The package declares MIRAGEA_API_KEY (required): Miragea API key from https://miragea.ai/workspace/api; MIRAGEA_OUTPUT_DIR: Folder for generated audio and subtitles (default ~/Miragea); MIRAGEA_BASE_URL: API root including /v1 (default https://miragea.ai/v1); MIRAGEA_WAIT_TIMEOUT: Max seconds to wait for a job before returning its task_id (default 600).
The published oci package is docker.io/miragea/tts-mcp-server:0.1.1. Its declared MCP transport is stdio.
The package declares MIRAGEA_API_KEY (required): Miragea API key from https://miragea.ai/workspace/api; MIRAGEA_BASE_URL: API root including /v1 (default https://miragea.ai/v1); MIRAGEA_WAIT_TIMEOUT: Max seconds to wait for a job before returning its task_id (default 600).
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project repository · Project website. This profile uses version 0.1.1 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related audio & speech MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| MIRAGEA_API_KEY | Miragea API key from https://miragea.ai/workspace/api | Yes |
| MIRAGEA_OUTPUT_DIR | Folder for generated audio and subtitles (default ~/Miragea) | Check documentation |
| MIRAGEA_BASE_URL | API root including /v1 (default https://miragea.ai/v1) | Check documentation |
| MIRAGEA_WAIT_TIMEOUT | Max seconds to wait for a job before returning its task_id (default 600) | Check documentation |
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.
An AI-native CRM your assistant can actually read from and write to.
MCP server for Supertonic 3 on-device text-to-speech
Model Context Protocol for Text-to-Speech
Official SynClub Model Context Protocol (MCP) Server that enables powerful AI generation capabilities including text-to-speech, voice cloning, video