Skip to content
mcp/harbor
LangChain

ffvoice for LangChain

io.github.chicogong/ffvoice

Offline speech-to-text & speaker diarization MCP server: transcribe audio on-device, no cloud

client:LangChain transport:stdio runtime:pypi

Install ffvoice in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "ffvoice": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["ffvoice"],
        }
})

tools = await client.get_tools()

get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs

ffvoice in other clients

ffvoice MCP server