Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@oto read this text aloud"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
oto is an MCP app that turns text into speech. From any MCP host (e.g. Claude), you ask it to read the current text aloud — it converts the text to audio with the OpenAI text-to-speech API and renders an audio player right in the conversation.
Text to audio — a text_to_speech tool takes the current text and generates an audio file via OpenAI TTS.
Inline player — the generated audio shows up as an interactive player UI inside the MCP host: play it, close it.
History — every audio you generate is saved; browse and replay your previous generations.
Authenticated — the server requires sign-in before use. Auth is handled by Supabase (used exclusively for authentication).
Related MCP server: MCP TTS Server
TypeScript end to end.
MCP server (remote, Streamable HTTP) with an embedded UI for the audio player.
OpenAI API for text-to-speech generation.
Supabase for authentication only.
Railway for hosting the backend, the database, and object storage for the audio files.
Early exploration — currently investigating the stack and setting up project configuration.
This server cannot be deployed
AI voice generation: text-to-speech and voice cloning from any MCP client.
The Listenetic MCP server is a remote, cloud-hosted server that enables AI assistants like ChatGPT and Claude to convert articles, documents, websites, and videos into high-quality AI-generated audio. It provides multi-format support for text and binary files, natural-sounding text-to-audio conversion using AI, and specialized processing for SSML, markup, markdown, and various media formats through three core tools: listentic_supported_mimetypes, listentic_add_content_text, and listentic_add_content_binary.
Hosted text-to-speech MCP server: 66 voices in 9 languages, long-form narration, podcasts.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
