How do I use Resemble AI with Claude?

You connect this MCP to your Claude client via Vinkius. Once connected, you can simply ask Claude to perform voice tasks like creating clips or listing projects.

Can I use SSML with this MCP?

Yes, the create_clip capability supports SSML for controlling speech characteristics.

How does the deepfake detection work?

The agent uses the detect_deepfake capability to analyze an audio clip and determine the probability that it was synthetically generated.

Do I need to manage my own API keys?

You will need to provide your Resemble AI API Token during the setup process to authenticate your account.

Can I create my own custom voices?

Yes, you can use the create_voice and create_recording capabilities to build and train custom voice profiles.

Can I use SSML tags when creating an audio clip?

Yes! The create_clip capability fully supports SSML in the body field, allowing you to control pitch, rate, and emphasis for more natural-sounding speech.

How can I transform an existing audio file into a different voice?

Use the speech_to_speech capability. Provide the target voice_uuid and a Base64 encoded audio sample or URL, and the AI will re-voice the content while keeping the original performance characteristics.

Is there a way to check if an audio file is a deepfake?

Absolutely. The detect_deepfake capability allows you to submit an audio URL to Resemble's security engine to analyze whether the speech was generated by AI.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Resemble AI 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 text into lifelike speech and manage audio assets directly.

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.

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.

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 · 16 capabilities

We ship only the actions that matter.

Capability set01 / 04

01-04

4 capabilities in this set.

Part of 16 available through Resemble AI.

01
Create project
This capability starts a new project to keep your audio assets organized.
02
Create voice
Use this to set up a new custom voice profile.
03
Delete voice
This capability removes a custom voice profile from your account.
04
Get clip
Get the specific details and data for a single audio clip.

Capability set02 / 04

05-08

4 capabilities in this set.

Part of 16 available through Resemble AI.

05
Get voice
Retrieve the configuration and details of a specific voice.
06
List clips
This capability returns a list of all audio clips within a project.
07
List recordings
Get a list of all training recordings associated with a voice.
08
List voices
Retrieve a full list of your custom and system voices.

Capability set03 / 04

09-12

4 capabilities in this set.

Part of 16 available through Resemble AI.

09
Update clip
Modify the properties of an existing audio clip.
10
Verify watermark
Check an audio file to see if it contains a specific digital watermark.
11
Add watermark
Apply an imperceptible digital watermark to an audio file for security.
12
Create clip
Generate a new audio clip from text using SSML support.

Capability set04 / 04

13-16

4 capabilities in this set.

Part of 16 available through Resemble AI.

13
Create recording
Upload an audio recording to use as training data for a voice.
14
Detect deepfake
Analyze an audio clip to determine if it was generated by AI.
15
List projects
Get a list of all your Resemble AI projects.
16
Speech to speech
Transform an input audio file into a different target voice.

Real work

What teams actually run

Automated Voiceovers

A creator sends a script to the agent to generate a voiceover for a video.

Voice Dubbing

A developer uses speech-to-speech to change the speaker of an audio file while keeping the tone.

Media Authentication

A security professional uses the agent to check if an audio file is a deepfake.

Custom Voice Training

A user uploads recordings to the agent to build a unique custom voice profile.

Automate a task

Put Resemble AI 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

Resemble AI 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.

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

You don't need a client to put Resemble AI 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

1107ms average. Fast in production.

Resemble AI is checked daily against the live service.

Daily averagePeak 1410ms

Oct 3Today

Fastest day: 851ms
Slowest day: 1410ms
14-day trend: Improving-20%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 16 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 Resemble AI, so you can see the experience inside your AI.

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

Resemble AI Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_lELKY7eitB2gZRvJGRTlTOUHxzdfjT5MrnBpOAJW/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Resemble AI capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "resemble-ai-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_lELKY7eitB2gZRvJGRTlTOUHxzdfjT5MrnBpOAJW/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 Resemble AI in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Resemble AI owners hand off.

This MCP is built for professionals working with synthetic media and audio security.

01
Content Creators
They hand off text scripts to the agent to generate voiceovers for localized content.
02
Developers
They use the agent to integrate voice synthesis and deepfake detection into their apps.
03
Security Teams
They task the agent with verifying audio authenticity and detecting synthetic manipulations.

FAQ

Questions Resemble AI owners ask.

01
How do I use Resemble AI with Claude?
You connect this MCP to your Claude client via Vinkius. Once connected, you can simply ask Claude to perform voice tasks like creating clips or listing projects.
02
Can I use SSML with this MCP?
Yes, the create_clip capability supports SSML for controlling speech characteristics.
03
How does the deepfake detection work?
The agent uses the detect_deepfake capability to analyze an audio clip and determine the probability that it was synthetically generated.
04
Do I need to manage my own API keys?
You will need to provide your Resemble AI API Token during the setup process to authenticate your account.
05
Can I create my own custom voices?
Yes, you can use the create_voice and create_recording capabilities to build and train custom voice profiles.
06
Can I use SSML tags when creating an audio clip?
Yes! The create_clip capability fully supports SSML in the body field, allowing you to control pitch, rate, and emphasis for more natural-sounding speech.
07
How can I transform an existing audio file into a different voice?
Use the speech_to_speech capability. Provide the target voice_uuid and a Base64 encoded audio sample or URL, and the AI will re-voice the content while keeping the original performance characteristics.
08
Is there a way to check if an audio file is a deepfake?
Absolutely. The detect_deepfake capability allows you to submit an audio URL to Resemble's security engine to analyze whether the speech was generated by AI.

Explore

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

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Create project

Create voice

Delete voice

Get clip

05-08

Get voice

List clips

List recordings

List voices

09-12

Update clip

Verify watermark

Add watermark

Create clip

13-16

Create recording

Detect deepfake

List projects

Speech to speech

What teams actually run

Automated Voiceovers

Voice Dubbing

Media Authentication

Custom Voice Training

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

Resemble AI Connector

Claude Desktop

Content Creators

Developers

Security Teams

How do I use Resemble AI with Claude?

Can I use SSML with this MCP?

How does the deepfake detection work?

Do I need to manage my own API keys?

Can I create my own custom voices?

Can I use SSML tags when creating an audio clip?

How can I transform an existing audio file into a different voice?

Is there a way to check if an audio file is a deepfake?

Play.ht (Voice Cloning) AI Connector

Speechmatics AI Connector

NVIDIA Audio AI Connector

LMNT (Ultra-low Latency Speech Synthesis) AI Connector

Suggestions

Cartesia (Voice AI) AI Connector

ElevenLabs AI Connector

AudioStack AI Connector

Lovo AI (Genny TTS & Voice Synthesis API) AI Connector