Ffvoice runs on your own machine — the client starts it, so there is no endpoint to ping. 879 installs a week from pypi. Last commit 19 May 2026.
Offline speech-to-text & speaker diarization MCP server: transcribe audio on-device, no cloud
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ffvoice -- uvx ffvoice
{
"mcpServers": {
"ffvoice": {
"args": [
"ffvoice"
],
"command": "uvx"
}
}
}
[mcp_servers.ffvoice]
command = "uvx"
args = ["ffvoice"]
{
"mcpServers": {
"ffvoice": {
"args": [
"ffvoice"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"ffvoice": {
"args": [
"ffvoice"
],
"command": "uvx"
}
}
}
Answers built from our own checks of this server.