FunASR vs Spoken

In-depth architectural comparison of the FunASR and Spoken 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.

Which MCP Server Should You Choose?

Choose FunASR 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).

Explore FunASR Details

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 (Freemium).
• Primary tools included: Search episodes by text or Spotify/YouTube URL, List complete podcast episode catalogs, Return timestamped Markdown transcripts.

Explore Spoken Details

Feature & Specification Comparison

Specification	FunASR Speech-to-Text	Spoken spokenmd Speech-to-Text
Summary	Transcribe local audio with FunASR and SenseVoice using private, on-device inference.	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.
Category & Scope	Speech-to-Text	Speech-to-Text

Tools & Capabilities Breakdown

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).

{
  "mcpServers": {
    "funasr": {
      "command": "uvx",
      "args": [
        "torch"
      ]
    }
  }
}

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

Related MCP Server Comparisons