Speech AI MCP Server

Speech AI MCP server exists for a simple reason — assistants are far more useful when they can act on Speech AI directly instead of describing what you should do. Pronunciation scoring, speech-to-text, and text-to-speech for AI agents.

What you get

Speech processing suite for AI coding assistants. Pronunciation assessment, speech-to-text, and text-to-speech — all via MCP.

• Pronunciation Assessment — Score English pronunciation at phoneme, word, and sentence levels (0-100). Exceeds human inter-annotator agreement
• Speech-to-Text — Transcribe English audio with word-level timestamps and confidence scores. Sub-300ms latency
• Text-to-Speech — Generate natural speech with 12 English voices (American and British). Speed control 0.5x-2.0x

What the assistant can call

Once Speech AI is connected, these are the calls the assistant has available:

• Cursor — The Cursor tool exposed by this server

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Configuration and credentials

You will need one environment variable: YOUR_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Choosing this one

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Speech AI's toolset — Cursor — is a fair guide to whether it matches your workflow. It is maintained by fasuizu-br; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Speech AI's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Before you rely on it

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the speech ai mcp server does with a few real requests.