diff --git a/CHANGELOG.md b/CHANGELOG.md
index 8fbc6d58f7f..b98a5622eec 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -70,6 +70,7 @@ Docs: https://docs.openclaw.ai
 - Browser/sandbox: clean up idle tracked tabs opened by primary-agent browser sessions, while preserving active tab reuse and lifecycle cleanup for subagents, cron, and ACP sessions. Fixes #71165. Thanks @dwbutler.
 - Plugins/Voice Call: pin voice response sessions to `responseModel` before embedded agent runs, avoiding live-session model switch failures when the global default model differs. Fixes #60118. Thanks @xinbenlv.
 - Media tools: honor the configured web-fetch SSRF policy for media understanding, image/music/video generation references, and PDF inputs, so explicit RFC2544 opt-ins cover WebChat OSS uploads without weakening defaults. Fixes #71300. (#71321) Thanks @neeravmakwana.
+- Agents/TTS: suppress successful spoken transcripts from verbose chat tool output when structured voice media is already queued, while preserving text output for non-builtin tool-name collisions. Fixes #71282. Thanks @neeravmakwana.
 - Gateway/sessions: recover main-agent turns interrupted by a gateway restart from stale transcript-lock evidence, avoiding stuck `status: "running"` sessions without broad post-boot transcript scans. Fixes #70555. Thanks @bitloi.
 - Codex approvals: keep command approval responses within Codex app-server `availableDecisions`, including deny/cancel fallbacks for prompts that do not offer `decline`. (#71338) Thanks @Lucenx9.
 - Plugins/Google Meet: include live Chrome-node readiness in `googlemeet setup` and document the Parallels recovery checks, so stale node tokens or disconnected VM browsers are visible before an agent opens a meeting. Thanks @steipete.
diff --git a/src/agents/pi-embedded-subscribe.handlers.tools.media.test.ts b/src/agents/pi-embedded-subscribe.handlers.tools.media.test.ts
index 6a607aed011..17b9e177d90 100644
--- a/src/agents/pi-embedded-subscribe.handlers.tools.media.test.ts
+++ b/src/agents/pi-embedded-subscribe.handlers.tools.media.test.ts
@@ -235,6 +235,7 @@ describe("handleToolExecutionEnd media emission", () => {
       shouldEmitToolOutput: true,
       onToolResult: vi.fn(),
       toolResultFormat: "plain",
+      builtinToolNames: new Set(["tts"]),
     });
 
     await handleToolExecutionEnd(ctx, {
@@ -263,6 +264,7 @@ describe("handleToolExecutionEnd media emission", () => {
       shouldEmitToolOutput: true,
       onToolResult: vi.fn(),
       toolResultFormat: "plain",
+      builtinToolNames: new Set(["tts"]),
     });
 
     await handleToolExecutionEnd(ctx, {
@@ -315,6 +317,40 @@ describe("handleToolExecutionEnd media emission", () => {
     expect(ctx.state.pendingToolAudioAsVoice).toBe(false);
   });
 
+  it("keeps verbose TTS text for non-builtin remote media collisions", async () => {
+    const ctx = createMockContext({
+      shouldEmitToolOutput: true,
+      onToolResult: vi.fn(),
+      toolResultFormat: "plain",
+      builtinToolNames: new Set(["web_search"]),
+    });
+
+    await handleToolExecutionEnd(ctx, {
+      type: "tool_execution_end",
+      toolName: "tts",
+      toolCallId: "tc-1",
+      isError: false,
+      result: {
+        content: [{ type: "text", text: "remote tool output" }],
+        details: {
+          media: {
+            mediaUrl: "https://example.com/reply.opus",
+            audioAsVoice: true,
+          },
+        },
+      },
+    });
+
+    expect(ctx.emitToolOutput).toHaveBeenCalledWith(
+      "tts",
+      undefined,
+      "remote tool output",
+      expect.any(Object),
+    );
+    expect(ctx.state.pendingToolMediaUrls).toEqual(["https://example.com/reply.opus"]);
+    expect(ctx.state.pendingToolAudioAsVoice).toBe(true);
+  });
+
   async function handleVerboseGeneratedImage(toolResultFormat: "plain" | "markdown") {
     const ctx = createMockContext({
       shouldEmitToolOutput: true,
diff --git a/src/agents/pi-embedded-subscribe.handlers.tools.ts b/src/agents/pi-embedded-subscribe.handlers.tools.ts
index 2aeb852b59a..b073bfe0010 100644
--- a/src/agents/pi-embedded-subscribe.handlers.tools.ts
+++ b/src/agents/pi-embedded-subscribe.handlers.tools.ts
@@ -191,10 +191,18 @@ function readApplyPatchSummary(result: unknown): ApplyPatchSummary | null {
 
 function shouldSuppressStructuredMediaToolOutput(params: {
   toolName: string;
+  rawToolName: string;
   isToolError: boolean;
   hasDeliverableStructuredMedia: boolean;
+  builtinToolNames?: ReadonlySet<string>;
 }): boolean {
-  return params.toolName === "tts" && !params.isToolError && params.hasDeliverableStructuredMedia;
+  return (
+    params.toolName === "tts" &&
+    params.rawToolName.trim() === "tts" &&
+    params.builtinToolNames?.has("tts") === true &&
+    !params.isToolError &&
+    params.hasDeliverableStructuredMedia
+  );
 }
 
 function buildPatchSummaryText(summary: ApplyPatchSummary): string {
@@ -527,8 +535,10 @@ async function emitToolResultOutput(params: {
   const shouldEmitOutput =
     !shouldSuppressStructuredMediaToolOutput({
       toolName,
+      rawToolName,
       isToolError,
       hasDeliverableStructuredMedia: hasStructuredMedia && mediaUrls.length > 0,
+      builtinToolNames: ctx.builtinToolNames,
     }) &&
     (ctx.shouldEmitToolOutput() || shouldEmitCompactToolOutput({ toolName, result, outputText }));
   if (shouldEmitOutput) {