Does this MCP require me to upload my files?

No. You don't need to manually upload files to a web portal. You give your AI client a public URL, and the MCP handles the transcription process directly from the link.

What is the difference between a transcript and a summary?

The transcript is the full, word-for-word text of the audio. The summary is a concise, high-fidelity overview, generated by the MCP, that captures the main points without the full text.

Can I use this for video files, or just audio?

It handles both. You can transcribe public audio or video URLs. The MCP extracts insights from both, including chapter markers and speaker separation.

How do I know when a transcription job is finished?

You use the list_transcripts capability to see your recent jobs. You can then use get_transcript with the job ID to check the status and retrieve the final result.

What kind of data does the sentiment analysis provide?

The get_sentiments capability analyzes the content and tells you the overall emotional tone, like 'Positive' or 'Negative'. It also provides timestamped segments where the tone changes.

How do I find my AssemblyAI API Key?

Log in to your account, navigate to the API Keys section in your dashboard, and copy your personal token.

Can I automatically summarize audio via AI?

Yes! Enable the summarization option when transcribing, then use the get_summary capability to retrieve the high-fidelity AI synopsis.

How do I check transcription status?

Use the get_transcript capability with the job ID provided at submission to monitor the status (Queued, Processing, Completed) in real-time.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect AssemblyAI (Alternative) to ChatGPT and Claude

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 raw audio and video into actionable, structured data.

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 · 9 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-03

3 capabilities in this set.

Part of 9 available through AssemblyAI.

01
Delete transcript
Removes a specific transcript record from your history.
02
Get sentiments
Analyzes the transcript to determine the overall emotional tone, identifying positive, negative, or neutral segments.
03
Get speakers
Separates the transcript by speaker, providing detailed labels so you know who said what during a conversation.

Capability set02 / 03

04-06

3 capabilities in this set.

Part of 9 available through AssemblyAI.

04
Get summary
Generates a concise, high-fidelity summary of the entire audio or video content.
05
Get transcript
Checks the status and retrieves the final result for a transcription job using a job ID.
06
List transcripts
Retrieves a list of your most recent transcription jobs and their status.

Capability set03 / 03

07-09

3 capabilities in this set.

Part of 9 available through AssemblyAI.

07
Get chapters
Automatically detects and retrieves chapter markers, helping you organize long-form video or podcast content.
08
Get topics
Identifies the main subjects discussed in the audio, providing a list of key topics covered.
09
Transcribe audio URL
Starts a transcription job for any public audio or video URL you provide.

Real work

What teams actually run

Meeting Minutes Generation

Send a recording URL and ask your agent to get the speakers and a summary. You get perfectly labeled minutes instantly.

Podcast Repurposing

Transcribe a full episode, then ask the MCP to get the chapters and key topics. You're ready to publish clips immediately.

Customer Call Analysis

Feed in a support call recording and ask for sentiment analysis. You can quickly identify if the customer was frustrated or satisfied.

Media Library Indexing

Process a directory of video URLs to get automated chapters and transcripts, keeping your media library perfectly organized.

Automate a task

Put AssemblyAI 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

AssemblyAI 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 AssemblyAI 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

997ms average. Fast in production.

AssemblyAI is checked daily against the live service.

Daily averagePeak 1396ms

Oct 3Today

Fastest day: 881ms
Slowest day: 1396ms
14-day trend: Stable+3%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 9 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 AssemblyAI, so you can see the experience inside your AI.

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

AssemblyAI Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_IctBwuEI5fLw0DEGx6JV9ytMfgfL9zH337qQ7vjt/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 — AssemblyAI capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "assemblyai-alternative-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_IctBwuEI5fLw0DEGx6JV9ytMfgfL9zH337qQ7vjt/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 AssemblyAI in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work AssemblyAI owners hand off.

This MCP is essential for anyone who deals with large amounts of spoken content. Content creators use it to quickly turn podcasts into chapters. Support teams use it to analyze customer calls for sentiment. Developers use it to build custom workflows that require structured speech data.

01
Content Creators
Generate podcast transcripts and video chapters using natural language commands.
02
Support & Sales Teams
Summarize meeting recordings and analyze customer sentiment without leaving your workspace.
03
Developers
Integrate high-speed speech-to-text intelligence into custom business workflows through simple AI queries.

FAQ

Questions AssemblyAI owners ask.

01
Does this MCP require me to upload my files?
No. You don't need to manually upload files to a web portal. You give your AI client a public URL, and the MCP handles the transcription process directly from the link.
02
What is the difference between a transcript and a summary?
The transcript is the full, word-for-word text of the audio. The summary is a concise, high-fidelity overview, generated by the MCP, that captures the main points without the full text.
03
Can I use this for video files, or just audio?
It handles both. You can transcribe public audio or video URLs. The MCP extracts insights from both, including chapter markers and speaker separation.
04
How do I know when a transcription job is finished?
You use the list_transcripts capability to see your recent jobs. You can then use get_transcript with the job ID to check the status and retrieve the final result.
05
What kind of data does the sentiment analysis provide?
The get_sentiments capability analyzes the content and tells you the overall emotional tone, like 'Positive' or 'Negative'. It also provides timestamped segments where the tone changes.
06
How do I find my AssemblyAI API Key?
Log in to your account, navigate to the API Keys section in your dashboard, and copy your personal token.
07
Can I automatically summarize audio via AI?
Yes! Enable the summarization option when transcribing, then use the get_summary capability to retrieve the high-fidelity AI synopsis.
08
How do I check transcription status?
Use the get_transcript capability with the job ID provided at submission to monitor the status (Queued, Processing, Completed) in real-time.

Explore

More in AI Frontier

Connect AssemblyAI to Claude, Cursor, ChatGPT & more

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.

01-03

Delete transcript

Get sentiments

Get speakers

04-06

Get summary

Get transcript

List transcripts

07-09

Get chapters

Get topics

Transcribe audio URL

What teams actually run

Meeting Minutes Generation

Podcast Repurposing

Customer Call Analysis

Media Library Indexing

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

AssemblyAI Connector

Claude Desktop

Content Creators

Support & Sales Teams

Developers

Does this MCP require me to upload my files?

What is the difference between a transcript and a summary?

Can I use this for video files, or just audio?

How do I know when a transcription job is finished?

What kind of data does the sentiment analysis provide?

How do I find my AssemblyAI API Key?

Can I automatically summarize audio via AI?

How do I check transcription status?

Speechmatics AI Connector

Fliki (AI Text-to-Video & Speech API) AI Connector

AssemblyAI AI Connector

Gladia (Speech AI) AI Connector

Suggestions

Speechnotes AI Connector

NVIDIA Audio AI Connector

Ebby AI Connector

3Scribe AI Connector