TTS API and MCP: how to add speech synthesis to your project

TTS is a text-to-speech model. NeuralSpace offers the following models: TTS, TTS HD. They all run through a single public API, and there is a ready MCP server for AI agents. The key is issued on the API keys page. Below are the model capabilities, request examples and setup steps.

What TTS can do

TTS synthesizes speech from text and immediately returns a link to the finished audio file. Two models are available: TTS and TTS HD (higher quality). Voices are alloy, echo, fable, onyx, nova and shimmer, formats are mp3, opus, aac, flac and wav. The price depends on the text length.

API endpoint

Send a request to POST /v1/audio/speech. Example: {"model": "tts-1", "input": "Hello! This is speech synthesis.", "voice": "alloy", "response_format": "mp3"}. Authorization uses an API key in the x-api-key header. Available model ids: tts-1, tts-1-hd.

MCP tools

The NeuralSpace MCP server is available at POST /mcp (Streamable HTTP). To work with TTS, an agent uses the tools: text_to_speech, list_models, get_balance. This lets Claude Code, Cursor and other MCP clients use the site models directly.

How to connect

Sign up on NeuralSpace, open the API keys page and create an nsk-… key. Then pass it in the request header or in your MCP client settings. Full documentation is on the the /v1/docs page.

FAQ

Which voices are available?

alloy, echo, fable, onyx, nova and shimmer.

Which formats are supported?

mp3, opus, aac, flac and wav.

What format is the request?

POST /v1/audio/speech with model and input fields.