mocoVoice MCP Server

mocoVoice MCP Server is an MCP server that connects Claude Desktop to the mocoVoice transcription API. It is designed for developers, researchers, and content creators who need to transcribe spoken audio and video recordings directly through an LLM interface. By providing an interface between the local file system and the mocoVoice speech-to-text service, the server allows Claude to inspect local directories for media files, verify supported extensions, submit asynchronous transcription jobs, monitor processing statuses, and pull final text transcripts back into the workspace. It supports large media files up to 5GB across a wide variety of audio and video formats, including WAV, MP3, FLAC, MP4, and MOV. Users can manage the complete transcription lifecycle entirely through conversational requests, eliminating the need to manually navigate external web consoles or write custom API scripts.

Category: Design, Media & Creative

Tags: audio, speech-to-text, transcription, video

Visit mocoVoice MCP Server

How to install and configure mocoVoice MCP Server

1. Ensure Docker and Claude Desktop are installed on your system. 2. Obtain a valid mocoVoice API KEY with read and write permissions. 3. Open your Claude Desktop configuration file (claude_desktop_config.json). 4. Add mocoVoice MCP Server under the mcpServers object: json { "mcpServers": { "mocoVoice MCP Server": { "command": "docker", "args": [ "run", "--pull", "always", "-i", "--rm", "--mount", "type=bind,src=<YOUR_DIR_PATH>,dst=/workspace", "-e", "MOCOVOICE_API_KEY", "-e", "MOCOVOICE_API_URL", "ghcr.io/mocomoco-inc/mocovoice-mcp-server" ], "env": { "MOCOVOICE_API_KEY": "<YOUR_API_KEY>", "MOCOVOICE_API_URL": "https://api.mocomoco.ai/api/v1" } } } } 5. Replace <YOUR_DIR_PATH> with the absolute path to your local media directory and <YOUR_API_KEY> with your mocoVoice API key, then restart Claude Desktop.

What you can do with mocoVoice MCP Server

• Transcribing recorded interviews or podcasts stored in local audio formats like MP3, WAV, or FLAC. - Extracting spoken dialogue from video footage such as MP4 and MOV files without manual audio extraction. - Listing and verifying all compatible media files within a designated workspace directory prior to batch processing. - Tracking asynchronous speech-to-text job statuses and reviewing historical processing tasks inside Claude Desktop. - Retrieving finalized transcript text directly into chat to summarize discussions or generate meeting minutes.

Key facts

• https://github.com/mocomoco-inc/mocovoice-mcp-server
• Design, Media & Creative, Files, Documents & PDFs
• audio, speech-to-text, transcription, video

Part of MCP Servers

What can mocoVoice MCP Server do?

mocoVoice MCP Server allows Claude Desktop to inspect local media directories, check compatible formats, submit audio and video files for transcription via the mocoVoice API, monitor job progress, and retrieve finished text transcripts directly into the LLM chat.

Which file formats does mocoVoice MCP Server support?

It supports files up to 5GB in size. Audio formats include WAV, MP3, M4A, CAF, AIFF, WMA, FLAC, OGG, and AAC. Video formats include AVI, MP4, RMVB, FLV, MOV, and WM.

What are the requirements to run mocoVoice MCP Server?

You need Docker installed and running, Claude Desktop, and a mocoVoice API key with both read and write permissions to authenticate against the mocoVoice API.

Is mocoVoice MCP Server free to use?

The server software is released under the MIT license, but running transcription jobs consumes your mocoVoice API quota and incurs API usage fees according to mocoVoice pricing.