What is the key difference between Spoken and Transcription?

Spoken belongs to the Speech-to-Text category with local stdio execution, while Transcription belongs to the Speech-to-Text category with local stdio execution.

How do I install Spoken or Transcription in Claude Desktop or Cursor?

Copy the mcpServers JSON configuration snippet provided on this page into your claude_desktop_config.json or ~/.cursor/mcp.json file and restart your AI client.

Are Spoken and Transcription free or paid?

Spoken operates under a Paid Service model (API Key required). Transcription operates under a Free / Open Source model (No auth required).

Which MCP server has more tools and community activity?

Spoken lists 6 tools with 3 views and 4 GitHub stars. Transcription lists 12 tools with 0 views and 13 GitHub stars.

Can I use both Spoken and Transcription together in the same MCP host?

Yes! MCP hosts like Claude Desktop, Cursor, Windsurf, Cline, and VS Code support configuring multiple servers under the mcpServers object simultaneously.

Side-by-Side Model Context Protocol Comparison

Spoken vs Transcription

In-depth architectural comparison of the Spoken and Transcription MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.

At a Glance & Executive Verdict

Spoken

Speech-to-Text · Local stdio

Quality: 55/100 (Good) | Auth: API Key required

Transcription

Speech-to-Text · Local stdio

Quality: 53/100 (Good) | Auth: No auth required

Verdict Summary: Choose Spoken if you need specialized Speech-to-Text tools running via a local process. Choose Transcription if your workspace requires Speech-to-Text integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.

Which MCP Server Should You Choose?

Choose Spoken when:

You need dedicated capabilities in the Speech-to-Text domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: API Key required (Paid Service).
You have access to required keys: SPOKEN_API_KEY.
Primary tools included: Returns transcripts with real speaker names, not generic labels, Outputs clean Markdown with timestamps for easy parsing, Supports search by text query or Spotify/YouTube URL.

Explore Spoken Details

Choose Transcription when:

You need dedicated capabilities in the Speech-to-Text domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Primary tools included: get_supported_languages, get_pricing, get_product_info.

Feature & Specification Comparison

Specification	Spoken spokenmd Speech-to-Text	Transcription Speech-to-Text
Summary	Fetch published podcast transcripts as clean Markdown with real speaker names (not "Speaker 1") via the Spoken API. Search episodes, get transcripts, check credit balance.	AI transcription from URLs. 99% accuracy, speaker diarization, 98+ languages.
Category & Scope	Speech-to-Text

Tools & Capabilities Breakdown

Spoken Tools (6)

Returns transcripts with real speaker names, not generic labels

Outputs clean Markdown with timestamps for easy parsing

Supports search by text query or Spotify/YouTube URL

Pay-per-use credit system with free repeat fetches

Includes an MCP server exposing tools for agent integration

Provides an OpenAPI spec and example agent skills

Transcription Tools (12)

Ready-to-Paste Client Configurations

Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).

Spoken Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "spokenmd-spoken": {
      "command": "npx",
      "args": [
        "-y",
        "spoken-mcp"
      ],
      "env": {
        "SPOKEN_API_KEY": "YOUR_SPOKEN_API_KEY_HERE"
      }
    }
  }
}

Transcription Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "transcription": {
      "command": "npx",
      "args": [
        "-y",
        "@scriptivox/mcp-server"
      ]
    }
  }
}

Frequently Asked Questions

Spoken is categorized under Speech-to-Text and uses a local stdio subprocess. In contrast, Transcription belongs to Speech-to-Text using local stdio subprocess. Select Spoken when you need capabilities focused on speech-to-text and Transcription when you require tools for speech-to-text.

More alternatives to Spoken More alternatives to Transcription Speech-to-Text category hub