Skip to content

The open-source AI voice studio. Clone, dictate, create.

docs: update the last two comment references to the dotted MCP tool names

jamiepined09c5c39e31a
diff --git a/backend/requirements.txt b/backend/requirements.txt
index 3c6160a5..ddc9bb6c 100644
--- a/backend/requirements.txt
+++ b/backend/requirements.txt
@@ -64,7 +64,7 @@ pedalboard>=0.9.0
httpx>=0.27.0
# MCP server (Model Context Protocol) — lets local AI agents call
-# voicebox.speak / .transcribe / .list_captures / .list_profiles
+# voicebox_speak / voicebox_transcribe / voicebox_list_captures / voicebox_list_profiles
fastmcp>=3.0,<4.0
sse-starlette>=2.0
diff --git a/tauri/src-tauri/src/main.rs b/tauri/src-tauri/src/main.rs
index 0f44ac90..a1edd132 100644
--- a/tauri/src-tauri/src/main.rs
+++ b/tauri/src-tauri/src/main.rs
@@ -1434,7 +1434,7 @@ pub fn run() {
}
});
- // Agent-initiated speech (voicebox.speak over MCP or POST /speak)
+ // Agent-initiated speech (voicebox_speak over MCP or POST /speak)
// pops the pill up so the user can see what's coming out of their
// machine. The `dictate:show` listener is kept for any frontend
// caller that wants to force-surface the pill directly, but the