diff --git a/desktop/src/features/dictation/hooks/useMessageComposerDictation.tsx b/desktop/src/features/dictation/hooks/useMessageComposerDictation.tsx
index a6d5d4277..960c390e6 100644
--- a/desktop/src/features/dictation/hooks/useMessageComposerDictation.tsx
+++ b/desktop/src/features/dictation/hooks/useMessageComposerDictation.tsx
@@ -1,7 +1,10 @@
 import type * as React from "react";
-import { useCallback, useRef } from "react";
+import { useCallback, useEffect, useRef } from "react";
 import { useFeatureEnabled } from "@/shared/features";
-import { getDictationSendDecision } from "../lib/voiceInput";
+import {
+  getDictationSendDecision,
+  shouldAutoSubmitDictation,
+} from "../lib/voiceInput";
 import { DictationButton } from "../ui/DictationButton";
 import { useComposerDictation } from "./useComposerDictation";
 
@@ -15,10 +18,14 @@ interface UseMessageComposerDictationOptions {
   setEditorContent: (text: string) => void;
   draftKey: string | null;
   composerRef: React.RefObject<HTMLElement | null>;
+  submitMessageRef: React.MutableRefObject<() => void>;
 }
 
 export function useMessageComposerDictation({
+  disabled,
+  draftKey,
   setEditorContent,
+  submitMessageRef,
   ...options
 }: UseMessageComposerDictationOptions) {
   const enabled = useFeatureEnabled("voiceDictation");
@@ -26,10 +33,34 @@ export function useMessageComposerDictation({
   setEditorContentRef.current = setEditorContent;
   const dictation = useComposerDictation({
     ...options,
+    disabled,
+    draftKey,
     enabled,
     setEditorContentRef,
   });
   const { isRecording, isStarting, isTranscribing, stopRecording } = dictation;
+  const sendAfterTranscriptionRef = useRef(false);
+
+  // biome-ignore lint/correctness/useExhaustiveDependencies: composer scope and availability are the reset triggers for a queued send
+  useEffect(() => {
+    sendAfterTranscriptionRef.current = false;
+  }, [disabled, draftKey]);
+
+  useEffect(() => {
+    if (
+      !shouldAutoSubmitDictation({
+        requested: sendAfterTranscriptionRef.current,
+        isRecording,
+        isStarting,
+        isTranscribing,
+      })
+    ) {
+      return;
+    }
+    sendAfterTranscriptionRef.current = false;
+    submitMessageRef.current();
+  }, [isRecording, isStarting, isTranscribing, submitMessageRef]);
+
   const prepareToSubmit = useCallback(() => {
     const decision = getDictationSendDecision({
       isRecording,
@@ -37,6 +68,7 @@ export function useMessageComposerDictation({
       isTranscribing,
     });
     if (decision === "stop-recording") {
+      sendAfterTranscriptionRef.current = true;
       stopRecording();
     }
     return decision === "send";
diff --git a/desktop/src/features/dictation/lib/voiceInput.test.mjs b/desktop/src/features/dictation/lib/voiceInput.test.mjs
index 908a7bd7f..3360d9ab0 100644
--- a/desktop/src/features/dictation/lib/voiceInput.test.mjs
+++ b/desktop/src/features/dictation/lib/voiceInput.test.mjs
@@ -4,6 +4,7 @@ import test from "node:test";
 import {
   getDictationSendDecision,
   replaceTrailingTranscribedText,
+  shouldAutoSubmitDictation,
 } from "./voiceInput.ts";
 
 test("dictation send stops capture before submitting", () => {
@@ -44,6 +45,32 @@ test("dictation send waits for the final transcript", () => {
   );
 });
 
+test("dictation auto-submit waits until capture and transcription settle", () => {
+  const state = {
+    requested: true,
+    isRecording: false,
+    isStarting: false,
+    isTranscribing: false,
+  };
+  assert.equal(shouldAutoSubmitDictation(state), true);
+  assert.equal(
+    shouldAutoSubmitDictation({ ...state, requested: false }),
+    false,
+  );
+  assert.equal(
+    shouldAutoSubmitDictation({ ...state, isRecording: true }),
+    false,
+  );
+  assert.equal(
+    shouldAutoSubmitDictation({ ...state, isStarting: true }),
+    false,
+  );
+  assert.equal(
+    shouldAutoSubmitDictation({ ...state, isTranscribing: true }),
+    false,
+  );
+});
+
 // ── replaceTrailingTranscribedText ──────────────────────────────────────────
 
 test("replaceTrailingTranscribedText_appendsWhenNoPrevious", () => {
diff --git a/desktop/src/features/dictation/lib/voiceInput.ts b/desktop/src/features/dictation/lib/voiceInput.ts
index c8d66a3ca..da92bdf7f 100644
--- a/desktop/src/features/dictation/lib/voiceInput.ts
+++ b/desktop/src/features/dictation/lib/voiceInput.ts
@@ -24,6 +24,20 @@ export function getDictationSendDecision({
   return "send";
 }
 
+export function shouldAutoSubmitDictation({
+  requested,
+  isRecording,
+  isStarting,
+  isTranscribing,
+}: {
+  requested: boolean;
+  isRecording: boolean;
+  isStarting: boolean;
+  isTranscribing: boolean;
+}): boolean {
+  return requested && !isRecording && !isStarting && !isTranscribing;
+}
+
 export function replaceTrailingTranscribedText(
   fullText: string,
   previousTranscribedText: string,
diff --git a/desktop/src/features/messages/ui/MessageComposer.tsx b/desktop/src/features/messages/ui/MessageComposer.tsx
index 1fbf8440d..5d92b3c25 100644
--- a/desktop/src/features/messages/ui/MessageComposer.tsx
+++ b/desktop/src/features/messages/ui/MessageComposer.tsx
@@ -232,7 +232,6 @@ function MessageComposerImpl({
       (replyTarget
         ? `Reply to ${replyTarget.author} in #${channelName}`
         : `Message #${channelName}`));
-
   const richText = useRichTextEditor({
     placeholder: computedPlaceholder,
     editable: !disabled,
@@ -277,6 +276,7 @@ function MessageComposerImpl({
     setEditorContent: richText.setContent,
     draftKey: effectiveDraftKey,
     composerRef: composerScrollRef,
+    submitMessageRef,
   });
   prepareDictationSubmitRef.current = dictation.prepareToSubmit;
   const linkEditor = useLinkEditor(richText);