fix(mlx): point Qwen 0.6B at the published mlx-community repo

The 0.6B slot was aliased to the 1.7B repo as a temporary fallback
because `mlx-community/Qwen3-TTS-12Hz-0.6B-Base-bf16` wasn't published
when MLX support shipped. That conversion is live now, so use it —
Apple Silicon users picking 0.6B get the actual 0.6B model (1.2 GB
instead of 3.5 GB).

Also drops the now-obsolete troubleshooting entry and updates the
triage notes in PROJECT_STATUS.md.

Fixes #485.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

app/src/components/AppFrame/AppFrame.tsx

@@ -1,5 +1,6 @@
 import { useRouterState } from '@tanstack/react-router';
 import { TitleBarDragRegion } from '@/components/TitleBarDragRegion';
+import { AudioKeepAlive } from '@/components/AudioPlayer/AudioKeepAlive';
 import { AudioPlayer } from '@/components/AudioPlayer/AudioPlayer';
 import { StoryTrackEditor } from '@/components/StoriesTab/StoryTrackEditor';
 import { TOP_SAFE_AREA_PADDING } from '@/lib/constants/ui';
@@ -26,6 +27,7 @@ export function AppFrame({ children }: AppFrameProps) {
       className={cn('h-screen bg-background flex flex-col overflow-hidden', TOP_SAFE_AREA_PADDING)}
     >
       <TitleBarDragRegion />
+      <AudioKeepAlive />
       {children}
       {showTrackEditor ? (
         <StoryTrackEditor storyId={story.id} items={story.items} />

app/src/components/AudioPlayer/AudioKeepAlive.tsx

@@ -0,0 +1,85 @@
+import { useEffect, useRef } from 'react';
+import { debug } from '@/lib/utils/debug';
+
+// WKWebView tears down the app's CoreAudio output when idle for long enough,
+// and a JS-level reload (cmd+R) does NOT restore it — only relaunching the
+// Tauri app does. Keeping a silent <audio> element looping forever prevents
+// the OS audio session from ever going dormant.
+//
+// Real silence (zero PCM samples) at full volume is preferred over a muted
+// element: browsers/WebKit can optimize muted media away, which defeats the
+// purpose of holding the session open.
+
+function buildSilentWavUrl(seconds = 1, sampleRate = 8000): string {
+  const numSamples = seconds * sampleRate;
+  const bytes = 44 + numSamples * 2;
+  const buffer = new ArrayBuffer(bytes);
+  const view = new DataView(buffer);
+  const write = (offset: number, str: string) => {
+    for (let i = 0; i < str.length; i++) view.setUint8(offset + i, str.charCodeAt(i));
+  };
+  write(0, 'RIFF');
+  view.setUint32(4, bytes - 8, true);
+  write(8, 'WAVE');
+  write(12, 'fmt ');
+  view.setUint32(16, 16, true);
+  view.setUint16(20, 1, true);
+  view.setUint16(22, 1, true);
+  view.setUint32(24, sampleRate, true);
+  view.setUint32(28, sampleRate * 2, true);
+  view.setUint16(32, 2, true);
+  view.setUint16(34, 16, true);
+  write(36, 'data');
+  view.setUint32(40, numSamples * 2, true);
+  return URL.createObjectURL(new Blob([buffer], { type: 'audio/wav' }));
+}
+
+export function AudioKeepAlive() {
+  const audioRef = useRef<HTMLAudioElement | null>(null);
+
+  useEffect(() => {
+    const url = buildSilentWavUrl(1, 8000);
+    const el = new Audio(url);
+    el.loop = true;
+    el.volume = 1;
+    el.preload = 'auto';
+    audioRef.current = el;
+
+    const tryPlay = () => {
+      if (!audioRef.current) return;
+      if (!audioRef.current.paused) return;
+      audioRef.current.play().catch((err) => {
+        debug.log('[AudioKeepAlive] play blocked (will retry on next gesture):', err);
+      });
+    };
+
+    tryPlay();
+
+    // Autoplay may be blocked until first user interaction — re-attempt then.
+    const onGesture = () => tryPlay();
+    window.addEventListener('pointerdown', onGesture, { once: false });
+    window.addEventListener('keydown', onGesture, { once: false });
+
+    // If the webview ever pauses the element on background, resume on return.
+    const onWake = () => {
+      if (!document.hidden) tryPlay();
+    };
+    document.addEventListener('visibilitychange', onWake);
+    window.addEventListener('focus', onWake);
+    window.addEventListener('pageshow', onWake);
+
+    return () => {
+      window.removeEventListener('pointerdown', onGesture);
+      window.removeEventListener('keydown', onGesture);
+      document.removeEventListener('visibilitychange', onWake);
+      window.removeEventListener('focus', onWake);
+      window.removeEventListener('pageshow', onWake);
+      el.pause();
+      el.src = '';
+      URL.revokeObjectURL(url);
+      audioRef.current = null;
+    };
+  }, []);
+
+  return null;
+}

backend/backends/__init__.py

@@ -177,7 +177,7 @@ def _get_qwen_model_configs() -> list[ModelConfig]:
     backend_type = get_backend_type()
     if backend_type == "mlx":
         repo_1_7b = "mlx-community/Qwen3-TTS-12Hz-1.7B-Base-bf16"
-        repo_0_6b = "mlx-community/Qwen3-TTS-12Hz-1.7B-Base-bf16"  # 0.6B not available in MLX, falls back
+        repo_0_6b = "mlx-community/Qwen3-TTS-12Hz-0.6B-Base-bf16"
     else:
         repo_1_7b = "Qwen/Qwen3-TTS-12Hz-1.7B-Base"
         repo_0_6b = "Qwen/Qwen3-TTS-12Hz-0.6B-Base"

backend/backends/mlx_backend.py

@@ -45,11 +45,9 @@ class MLXTTSBackend:
         Returns:
             HuggingFace Hub model ID for MLX
         """
-        # MLX model mapping
         mlx_model_map = {
             "1.7B": "mlx-community/Qwen3-TTS-12Hz-1.7B-Base-bf16",
-            # 0.6B not yet converted to MLX format
-            "0.6B": "mlx-community/Qwen3-TTS-12Hz-1.7B-Base-bf16",  # Fallback to 1.7B
+            "0.6B": "mlx-community/Qwen3-TTS-12Hz-0.6B-Base-bf16",
         }
 
         if model_size not in mlx_model_map:

backend/tests/test_qwen_download.py

@@ -175,7 +175,7 @@ async def main():
     print("   ✅ Server is running")
 
     # Test model
-    model_name = "qwen-tts-0.6B"  # Note: 0.6B currently maps to 1.7B on MLX
+    model_name = "qwen-tts-0.6B"
     
     # Check current status
     print(f"\n📊 Checking status of {model_name}...")

docs/PROJECT_STATUS.md

@@ -309,11 +309,7 @@ Still reported. Users get stuck downloads, can't resume, offline mode edge cases
 
 **Fix path:** PR #443 addresses infinite offline retry. CustomVoice-specific download failures (#475, #445) need triage — likely related to frozen-binary import fixes in PR #438. TADA cluster (#336, #348) and macOS ARM import regressions (#287, #275, #304) need a dedicated triage pass.
 
-**Qwen 0.6B-downloads-1.7B reports:** **#485** (2026-04-19), **#423** (macOS M1), **#329**. Platform-dependent:
-
-- **On MLX (Apple Silicon) — not a bug.** `mlx-community` only publishes 1.7B-Base-bf16 weights, so the 0.6B Base option intentionally resolves to the same repo (`backend/backends/__init__.py:180` — `# 0.6B not available in MLX, falls back`). UX gap: the selector offers a size that doesn't exist on the active backend. Fix: (a) hide the 0.6B option on MLX, or (b) label it "0.6B (uses 1.7B on Apple Silicon)".
-- **On PyTorch (Windows/Linux/CUDA/ROCm/XPU/CPU) — real bug if reported.** Both 0.6B and 1.7B have distinct repos (`Qwen/Qwen3-TTS-12Hz-0.6B-Base` vs `-1.7B-Base`). Triage each report by platform before merging into the MLX cluster.
-- **Qwen CustomVoice (either platform)** — no fallback, both sizes always have dedicated repos.
+**Qwen 0.6B-downloads-1.7B reports:** **#485** (2026-04-19), **#423** (macOS M1), **#329**. Originally a stale-fallback bug: `mlx-community/Qwen3-TTS-12Hz-0.6B-Base-bf16` wasn't published when MLX support shipped, so the 0.6B slot was aliased to the 1.7B repo. The 0.6B bf16 conversion is live now and both `backend/backends/mlx_backend.py` and `backend/backends/__init__.py` point at their correct repos. Qwen CustomVoice is unaffected — it runs via PyTorch on all platforms, both sizes always have dedicated repos.
 
 ### Language Requests (ongoing)
 
@@ -393,7 +389,7 @@ Notable:
 | **#306** ("voice model"), **#389** ("New model"), **#473** ("New functionality") | Title-only issues, no content. Request details or close. |
 | **#309** | Uninstall/cleanup question. Answer and close. |
 | **#241** | "How to use in Colab" — support question, not a bug. |
-| **#423** / **#485** / **#329** | Platform-dependent. On MLX: not a bug (0.6B weights don't exist upstream, fallback is intentional — fix UX). On PyTorch: real bug if reproducible. Classify each by reporter's platform before deduping. |
+| **#423** / **#485** / **#329** | Stale MLX fallback to 1.7B repo — fixed; 0.6B bf16 conversion now live on `mlx-community`, registry points at correct repo on both backends. |
 | **#336** / **#348** | TADA download/registration cluster — triage together. |
 | **#287** / **#275** / **#304** | macOS ARM import regressions on new version — likely one root cause. |
 | **#292**, **#349** | Possibly already fixed by merged PRs (#321/#412 and #345). Verify + close. |

docs/content/docs/overview/troubleshooting.mdx

@@ -446,20 +446,6 @@ Restart the app to create a fresh database.
   huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-Base
   ```
 
-### Qwen 0.6B Downloads the Same Files as 1.7B on Apple Silicon
-
-**Symptoms:**
-- You select Qwen 0.6B on an Apple Silicon Mac and the download is the same size as 1.7B
-- Generation speed and VRAM usage match 1.7B, not the expected smaller model
-
-**Explanation:**
-This is intentional, not a bug. The MLX community only publishes `mlx-community/Qwen3-TTS-12Hz-1.7B-Base-bf16` — there is no 0.6B MLX build. Voicebox's model registry falls back to the 1.7B weights when 0.6B is selected on MLX (see `backend/backends/__init__.py`).
-
-**Solution:**
-- On Apple Silicon, both size options use the 1.7B model — pick either.
-- If you specifically need a smaller model, switch to **Kokoro 82M** (~350 MB) or **LuxTTS** (~300 MB) — both CPU-realtime.
-- On Windows/Linux with PyTorch, 0.6B and 1.7B are distinct repos and behave differently.
-
 ### Wrong Model Version
 
 **Symptoms:**

landing/src/app/download/[platform]/route.ts

@@ -15,17 +15,32 @@ const PLATFORM_ALIAS: Record<string, string> = {
   windows: 'windows',
 };
 
+function getPublicOrigin(request: NextRequest): string {
+  const forwardedHost = request.headers.get('x-forwarded-host');
+  const forwardedProto = request.headers.get('x-forwarded-proto');
+
+  if (forwardedHost && forwardedProto) {
+    // Behind reverse proxies/CDNs, request.url can be an internal origin
+    // (for example localhost:8080). Prefer forwarded headers so redirects
+    // keep users on the public domain.
+    return `${forwardedProto}://${forwardedHost}`;
+  }
+
+  return new URL(request.url).origin;
+}
+
 export async function GET(
   request: NextRequest,
   { params }: { params: Promise<{ platform: string }> },
 ) {
+  const origin = getPublicOrigin(request);
   const { platform } = await params;
   // No prebuilt Linux binary yet — send straight to the build-from-source page.
   if (platform === 'linux') {
-    return NextResponse.redirect(new URL('/linux-install', request.url), 307);
+    return NextResponse.redirect(new URL('/linux-install', origin), 307);
   }
   const normalized = PLATFORM_ALIAS[platform];
-  const target = new URL('/download', request.url);
+  const target = new URL('/download', origin);
   if (normalized) target.searchParams.set('platform', normalized);
   return NextResponse.redirect(target, 307);
 }