diff --git a/scripts/openclaw-npm-release-check.ts b/scripts/openclaw-npm-release-check.ts
index b32574be439..4733141a491 100644
--- a/scripts/openclaw-npm-release-check.ts
+++ b/scripts/openclaw-npm-release-check.ts
@@ -427,16 +427,14 @@ function isNpmExecPath(value: string): boolean {
   return /^npm(?:-cli)?(?:\.(?:c?js|cmd|exe))?$/.test(basename(value).toLowerCase());
 }
 
-export function resolveNpmCommandInvocation(
-  params: {
-    npmExecPath?: string;
-    nodeExecPath?: string;
-    platform?: NodeJS.Platform;
-  } = {},
-): { command: string; args: string[] } {
-  const npmExecPath = params.npmExecPath ?? process.env.npm_execpath;
-  const nodeExecPath = params.nodeExecPath ?? process.execPath;
-  const npmCommand = (params.platform ?? process.platform) === "win32" ? "npm.cmd" : "npm";
+export function resolveNpmCommandInvocation(params?: {
+  npmExecPath?: string;
+  nodeExecPath?: string;
+  platform?: NodeJS.Platform;
+}): { command: string; args: string[] } {
+  const npmExecPath = params === undefined ? process.env.npm_execpath : params.npmExecPath;
+  const nodeExecPath = params?.nodeExecPath ?? process.execPath;
+  const npmCommand = (params?.platform ?? process.platform) === "win32" ? "npm.cmd" : "npm";
 
   if (typeof npmExecPath === "string" && npmExecPath.length > 0 && isNpmExecPath(npmExecPath)) {
     return { command: nodeExecPath, args: [npmExecPath] };
diff --git a/src/gateway/server-methods/chat-transcribe-audio.runtime.ts b/src/gateway/server-methods/chat-transcribe-audio.runtime.ts
new file mode 100644
index 00000000000..647a8cab66d
--- /dev/null
+++ b/src/gateway/server-methods/chat-transcribe-audio.runtime.ts
@@ -0,0 +1 @@
+export { transcribeAudioFile } from "../../media-understanding/runtime.js";
diff --git a/src/gateway/server-methods/chat-transcribe-audio.ts b/src/gateway/server-methods/chat-transcribe-audio.ts
index bd72c183d88..13dbb2a84e3 100644
--- a/src/gateway/server-methods/chat-transcribe-audio.ts
+++ b/src/gateway/server-methods/chat-transcribe-audio.ts
@@ -1,7 +1,6 @@
 import fs from "node:fs/promises";
 import os from "node:os";
 import path from "node:path";
-import { transcribeAudioFile } from "../../media-understanding/runtime.js";
 import { extensionForMime, normalizeMimeType } from "../../media/mime.js";
 import { normalizeOptionalString } from "../../shared/string-coerce.js";
 import { ErrorCodes, errorShape } from "../protocol/index.js";
@@ -9,6 +8,18 @@ import { MAX_PAYLOAD_BYTES } from "../server-constants.js";
 import { formatForLog } from "../ws-log.js";
 import type { GatewayRequestHandlers } from "./types.js";
 
+type ChatTranscribeAudioRuntime = typeof import("./chat-transcribe-audio.runtime.js");
+type TranscribeAudioFileResult = Awaited<
+  ReturnType<ChatTranscribeAudioRuntime["transcribeAudioFile"]>
+>;
+
+let chatTranscribeAudioRuntimePromise: Promise<ChatTranscribeAudioRuntime> | null = null;
+
+function loadChatTranscribeAudioRuntime(): Promise<ChatTranscribeAudioRuntime> {
+  chatTranscribeAudioRuntimePromise ??= import("./chat-transcribe-audio.runtime.js");
+  return chatTranscribeAudioRuntimePromise;
+}
+
 const CHAT_TRANSCRIBE_AUDIO_WS_JSON_OVERHEAD_BYTES = 64 * 1024;
 export const MAX_CHAT_TRANSCRIBE_AUDIO_BYTES = Math.floor(
   ((MAX_PAYLOAD_BYTES - CHAT_TRANSCRIBE_AUDIO_WS_JSON_OVERHEAD_BYTES) * 3) / 4,
@@ -45,9 +56,7 @@ function extensionForAudioMime(mime?: string): string {
   return extensionForMime(mime) ?? ".audio";
 }
 
-function isMissingMediaUnderstandingProvider(
-  result: Awaited<ReturnType<typeof transcribeAudioFile>>,
-) {
+function isMissingMediaUnderstandingProvider(result: TranscribeAudioFileResult) {
   const decision = result.decision;
   return (
     decision?.outcome === "skipped" &&
@@ -86,6 +95,7 @@ export const chatTranscribeAudioHandlers: GatewayRequestHandlers = {
     const filePath = path.join(tmpDir, `dictation${extensionForAudioMime(decoded.mime)}`);
     try {
       await fs.writeFile(filePath, decoded.data);
+      const { transcribeAudioFile } = await loadChatTranscribeAudioRuntime();
       const result = await transcribeAudioFile({
         filePath,
         cfg: context.getRuntimeConfig(),