Log inSubmit server

Speech-to-Text MCP servers

Discover 67 Speech-to-Text MCP servers for AI agents. Browse, compare, and install Model Context Protocol tools that connect Claude, Cursor, and other clients to speech-to-text capabilities. Popular picks include Whisper Windows MCP, Spoken, MCP Listen.

Search & filter all 67

Top picks

The most-used Speech-to-Text servers on AllMCPs right now.

  1. Whisper Windows MCP logo

    Whisper Windows MCP

    eviscerations

    Windows-native local audio and video transcription using whisper.cpp with Vulkan GPU acceleration. No cloud APIs, no Python. Batch processing, multilingual support, model management, and background job handling built in.

    Upvotes: 1Installs: 3GitHub stars: 1
  2. Spoken logo

    Spoken

    spokenmd

    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.

    Upvotes: 0Installs: 0GitHub stars: 5
  3. MCP Listen logo

    MCP Listen

    Give your AI agents the ability to listen. Microphone capture and speech-to-text.

    Upvotes: 0Installs: 0GitHub stars: 10

More Speech-to-Text servers

Filter by client, language & more
Showing 60 of 67Browse all 67 Speech-to-Text servers

Frequently Asked Questions about Speech-to-Text MCP Servers

Model Context Protocol (MCP) servers in the Speech-to-Text category allow AI assistants (such as Claude Desktop, Cursor, Windsurf, and Cline) to connect directly to speech-to-text tools, APIs, and databases without manual copy-pasting.

To install a Speech-to-Text MCP server, select your desired server from the directory, copy the JSON configuration snippet, and add it to your client config file (such as claude_desktop_config.json or .cursor/mcp.json).

Yes, all Speech-to-Text MCP servers listed in this directory are open-source and free to integrate into compatible Model Context Protocol clients.