An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Speechmatics to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn spoken words into text and text into natural speech.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 8 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 8 available through Speechmatics.

  1. 01

    Delete job

    This capability removes a specific transcription job from your history.

  2. 02

    Generate tts

    This capability converts your text into natural human speech using voices like Sarah, Theo, Megan, or Jack.

  3. 03

    Get job

    This capability retrieves the current status and details for a specific transcription job.

  4. 04

    Get usage

    This capability pulls your current account consumption and usage statistics.

Capability set02 / 02

05-08

4 capabilities in this set.

Part of 8 available through Speechmatics.

  1. 05

    List jobs

    This capability shows a list of your most recent transcription jobs.

  2. 06

    Create temp key

    This capability generates a temporary API key for secure, limited-time access.

  3. 07

    Get transcript

    This capability fetches the completed text from a transcription job in formats like JSON, text, or SRT.

  4. 08

    Create job

    This capability starts a new batch transcription job using an audio URL or base64 data.

Real work

What teams actually run

01

Video Subtitling

An agent transcribes a video file and outputs an SRT file for immediate use in video editors.

02

Meeting Analysis

You send a recording of a call to the agent to get a text version for searching and summarizing.

03

Voice Generation

An agent takes a written script and generates an audio file using a specific human voice.

04

Automated Transcription

You submit large batches of audio files to be processed as background jobs.

Automate a task

Put Speechmatics to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Speechmatics works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Speechmatics to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

923ms average. Fast in production.

Speechmatics is checked daily against the live service.

Daily averagePeak 1092ms
Oct 3Today
Fastest day
816ms
Slowest day
1092ms
14-day trend
Slowing+14%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 8 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Speechmatics, so you can see the experience inside your AI.

It does not authenticate your account with Speechmatics. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Speechmatics Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_FRLuaMwEkSVVnPCae4yQUSbZdPUlWPw9NvqN4KDY/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Speechmatics capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "speechmatics-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_FRLuaMwEkSVVnPCae4yQUSbZdPUlWPw9NvqN4KDY/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Speechmatics in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Speechmatics owners hand off.

This MCP is built for anyone needing to bridge the gap between audio and text within an AI workflow.

  • 01

    Content Creators

    They hand off video files to the agent to get SRT subtitles or podcast transcripts.

  • 02

    Developers

    They use the MCP to add speech features to apps without building audio backends.

  • 03

    Data Analysts

    They hand off recorded meetings to the agent to turn them into searchable text.

FAQ

Questions Speechmatics owners ask.

  • 01

    How do I use Speechmatics with my AI agent?

    You connect the MCP to your client, provide your Speechmatics API key, and then you can simply ask your agent to perform tasks like transcribing audio or generating speech.

  • 02

    What audio formats can I transcribe?

    You can submit audio via a URL or by providing base64 data for the agent to process.

  • 03

    Can I get subtitles from my transcriptions?

    Yes, you can use the capability to retrieve transcripts in SRT format, which is ideal for subtitles.

  • 04

    What voices are available for text-to-speech?

    The MCP provides access to natural voices including Sarah, Theo, Megan, and Jack.

  • 05

    How do I check if my transcription is finished?

    You can use the capability to list recent jobs or check the specific status of a single job.

  • 06

    What formats can I get my transcripts in?

    You can use the get_transcript capability to retrieve results in json, txt, or srt (subtitle) formats. Simply specify the format parameter when calling the capability.

  • 07

    Which voices are available for Text-to-Speech?

    The generate_tts capability supports four high-quality voices: sarah, theo, megan, and jack. You can choose the one that best fits your content's tone.

  • 08

    How do I check if my transcription job is finished?

    Use the get_job capability with your specific job_id. It will return the current status (e.g., running, completed) and metadata about the processing task.

Explore

More in Productivity

Suggestions

Connect Speechmatics to Claude, Cursor, ChatGPT & more