create stub resource files when actool output is missing

Older Xcode versions don't produce Assets.car from .icon assets.
Fall back to empty stubs for all platforms so the bundler succeeds.

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.2.3
+current_version = 0.3.0
 commit = True
 tag = True
 tag_name = v{new_version}

.github/workflows/release.yml

@@ -189,10 +189,10 @@ jobs:
           pip install -r backend/requirements.txt
           pip install --no-deps chatterbox-tts
 
-      - name: Install PyTorch with CUDA 12.1
+      - name: Install PyTorch with CUDA 12.6
         run: |
-          pip install torch --index-url https://download.pytorch.org/whl/cu121 --force-reinstall --no-deps
-          pip install torchaudio --index-url https://download.pytorch.org/whl/cu121
+          pip install torch --index-url https://download.pytorch.org/whl/cu126 --force-reinstall --no-deps
+          pip install torchaudio --index-url https://download.pytorch.org/whl/cu126 --force-reinstall --no-deps
 
       - name: Verify CUDA support in torch
         run: |

.gitignore

@@ -50,6 +50,8 @@ logs/
 app/openapi.json
 tauri/src-tauri/binaries/*
 tauri/src-tauri/gen/Assets.car
+tauri/src-tauri/gen/voicebox.icns
+tauri/src-tauri/gen/partial.plist
 
 # Temporary
 tmp/

CHANGELOG.md

@@ -7,9 +7,25 @@
 
 ## [Unreleased]
 
-This release rewrites the backend into a modular architecture, migrates the documentation site to Fumadocs, and ships a batch of bug fixes and UI polish across the stack.
+## [0.3.0] - 2026-03-17
 
-The backend's 3,000-line monolith `main.py` has been decomposed into domain routers, a services layer, and a proper database package. A style guide and ruff configuration now enforce consistency. On the frontend, model loading status is now visible in the UI, effects presets get a dropdown, and several race conditions and accessibility gaps are closed.
+This release rewrites the backend into a modular architecture, overhauls the settings UI into routed sub-pages, fixes audio player freezing, migrates documentation to Fumadocs, and ships a batch of bug fixes targeting the most-reported issues from the tracker.
+
+The backend's 3,000-line monolith `main.py` has been decomposed into domain routers, a services layer, and a proper database package. A style guide and ruff configuration now enforce consistency. On the frontend, settings have been split into dedicated routed pages with server logs, a changelog viewer, and an about page. The audio player no longer freezes mid-playback, and model loading status is now visible in the UI. Seven user-reported bugs have been fixed, including server crashes during sample uploads, generation list staleness, cryptic error messages, and CUDA support for RTX 50-series GPUs.
+
+### Settings Overhaul ([#294](https://github.com/jamiepine/voicebox/pull/294))
+- Split settings into routed sub-tabs: General, Generation, GPU, Logs, Changelog, About
+- Added live server log viewer with auto-scroll
+- Added in-app changelog page that parses `CHANGELOG.md` at build time
+- Added About page with version info, license, and generation folder quick-open
+- Extracted reusable `SettingRow` component for consistent setting layouts
+
+### Audio Player Fix ([#293](https://github.com/jamiepine/voicebox/pull/293))
+- Fixed audio player freezing during playback
+- Improved playback UX with better state management and listener cleanup
+- Fixed restart race condition during regeneration
+- Added stable keys for audio element re-rendering
+- Improved accessibility across player controls
 
 ### Backend Refactor ([#285](https://github.com/jamiepine/voicebox/pull/285))
 - Extracted all routes from `main.py` into 13 domain routers under `backend/routes/` — `main.py` dropped from ~3,100 lines to ~10
@@ -40,6 +56,17 @@ The backend's 3,000-line monolith `main.py` has been decomposed into domain rout
 - Softened select focus indicator opacity
 - Addressed 4 critical and 12 major issues from CodeRabbit review
 
+### Bug Fixes ([#295](https://github.com/jamiepine/voicebox/pull/295))
+- Fixed sample uploads crashing the server — audio decoding now runs in a thread pool instead of blocking the async event loop ([#278](https://github.com/jamiepine/voicebox/issues/278))
+- Fixed generation list not updating when a generation completes — switched to `refetchQueries` for reliable cache busting, added SSE error fallback, and page reset on completion ([#231](https://github.com/jamiepine/voicebox/issues/231))
+- Fixed error toasts showing `[object Object]` instead of the actual error message ([#290](https://github.com/jamiepine/voicebox/issues/290))
+- Added Whisper model selection (`base`, `small`, `medium`, `large`, `turbo`) and expanded language support to the `/transcribe` endpoint ([#233](https://github.com/jamiepine/voicebox/issues/233))
+- Upgraded CUDA backend build from cu121 to cu126 for RTX 50-series (Blackwell) GPU support ([#289](https://github.com/jamiepine/voicebox/issues/289))
+- Handled client disconnects in SSE and streaming endpoints to suppress `[Errno 32] Broken Pipe` errors ([#248](https://github.com/jamiepine/voicebox/issues/248))
+- Fixed Docker build failure from pip hash mismatch on Qwen3-TTS dependencies ([#286](https://github.com/jamiepine/voicebox/issues/286))
+- Added 50 MB upload size limit with chunked reads to prevent unbounded memory allocation on sample uploads
+- Eliminated redundant double audio decode in sample processing pipeline
+
 ### Platform Fixes
 - Replaced `netstat` with `TcpStream` + PowerShell for Windows port detection ([#277](https://github.com/jamiepine/voicebox/pull/277))
 - Fixed Docker frontend build and cleaned up Docker docs

Dockerfile

@@ -31,6 +31,8 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     build-essential \
     && rm -rf /var/lib/apt/lists/*
 
+RUN pip install --no-cache-dir --upgrade pip
+
 COPY backend/requirements.txt .
 RUN pip install --no-cache-dir --prefix=/install -r requirements.txt
 RUN pip install --no-cache-dir --prefix=/install \

app/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@voicebox/app",
-  "version": "0.2.3",
+  "version": "0.3.0",
   "private": true,
   "type": "module",
   "scripts": {

app/src/components/History/HistoryTable.tsx

@@ -153,7 +153,9 @@ export function HistoryTable() {
     }
   }, [historyData, page]);
 
-  // Reset to page 0 when deletions or imports occur
+  // Reset to page 0 when deletions, imports, or generation completions occur
+  const pendingCount = useGenerationStore((state) => state.pendingGenerationIds.size);
+  const prevPendingCountRef = useRef(pendingCount);
   useEffect(() => {
     if (deleteGeneration.isSuccess || importGeneration.isSuccess) {
       setPage(0);
@@ -161,6 +163,19 @@ export function HistoryTable() {
     }
   }, [deleteGeneration.isSuccess, importGeneration.isSuccess]);
 
+  useEffect(() => {
+    // A generation finished (pending count decreased) — scroll back to show it
+    if (
+      prevPendingCountRef.current > 0 &&
+      pendingCount < prevPendingCountRef.current &&
+      page !== 0
+    ) {
+      setPage(0);
+      setAllHistory([]);
+    }
+    prevPendingCountRef.current = pendingCount;
+  }, [pendingCount, page]);
+
   // Intersection Observer for infinite scroll
   useEffect(() => {
     const loadMoreEl = loadMoreRef.current;

app/src/components/ServerTab/AboutPage.tsx

@@ -124,7 +124,7 @@ export function AboutPage() {
                 rel="noopener noreferrer"
                 className="hover:text-muted-foreground/60 transition-colors"
               >
-                BSL 1.1
+                MIT
               </a>
             </p>
           </FadeIn>

app/src/components/ServerTab/ChangelogPage.tsx

@@ -57,8 +57,8 @@ function renderMarkdown(md: string): React.ReactNode[] {
       }
       elements.push(
         <ul key={elements.length} className="space-y-1 my-2">
-          {items.map((item) => (
-            <li key={item} className="text-sm text-muted-foreground flex gap-2">
+          {items.map((item, idx) => (
+            <li key={idx} className="text-sm text-muted-foreground flex gap-2">
               <span className="text-muted-foreground/50 select-none shrink-0">&bull;</span>
               <span>{inlineMarkdown(item)}</span>
             </li>
@@ -96,9 +96,9 @@ function renderTable(tableLines: string[], keyBase: number): React.ReactNode {
       <table className="text-sm w-full">
         <thead>
           <tr className="border-b">
-            {headers.map((h) => (
+            {headers.map((h, hIdx) => (
               <th
-                key={h}
+                key={hIdx}
                 className="text-left py-1.5 pr-4 text-muted-foreground font-medium text-xs"
               >
                 {inlineMarkdown(h)}
@@ -107,10 +107,10 @@ function renderTable(tableLines: string[], keyBase: number): React.ReactNode {
           </tr>
         </thead>
         <tbody>
-          {rows.map((row) => (
-            <tr key={row.join('|')} className="border-b border-border/50">
-              {row.map((cell) => (
-                <td key={cell} className="py-1.5 pr-4 text-muted-foreground">
+          {rows.map((row, rowIdx) => (
+            <tr key={rowIdx} className="border-b border-border/50">
+              {row.map((cell, cellIdx) => (
+                <td key={cellIdx} className="py-1.5 pr-4 text-muted-foreground">
                   {inlineMarkdown(cell)}
                 </td>
               ))}

app/src/components/ServerTab/GeneralPage.tsx

@@ -133,6 +133,13 @@ export function GeneralPage() {
                 setKeepServerRunningOnClose(checked);
                 platform.lifecycle.setKeepServerRunning(checked).catch((error) => {
                   console.error('Failed to sync setting to Rust:', error);
+                  setKeepServerRunningOnClose(!checked);
+                  toast({
+                    title: 'Failed to update setting',
+                    description: 'Could not sync setting to backend.',
+                    variant: 'destructive',
+                  });
+                  return;
                 });
                 toast({
                   title: 'Setting updated',

app/src/components/ServerTab/GpuPage.tsx

@@ -171,17 +171,21 @@ export function GpuPage() {
     };
   }, [cudaDownloading, serverUrl, refetchCudaStatus]);
 
+  const clearHealthPolling = useCallback(() => {
+    if (healthPollRef.current) {
+      clearInterval(healthPollRef.current);
+      healthPollRef.current = null;
+    }
+  }, []);
+
   const startHealthPolling = useCallback(() => {
-    if (healthPollRef.current) return;
+    clearHealthPolling();
 
     healthPollRef.current = setInterval(async () => {
       try {
         const result = await apiClient.getHealth();
         if (result.status === 'healthy') {
-          if (healthPollRef.current) {
-            clearInterval(healthPollRef.current);
-            healthPollRef.current = null;
-          }
+          clearHealthPolling();
           setRestartPhase('ready');
           queryClient.invalidateQueries();
           setTimeout(() => setRestartPhase('idle'), 2000);
@@ -190,7 +194,23 @@ export function GpuPage() {
         // Server still down, keep polling
       }
     }, 1000);
-  }, [queryClient]);
+  }, [queryClient, clearHealthPolling]);
+
+  const restartServerWithPolling = useCallback(
+    async (errorMessage: string) => {
+      setRestartPhase('stopping');
+      try {
+        await platform.lifecycle.restartServer();
+        setRestartPhase('waiting');
+        startHealthPolling();
+      } catch (e: unknown) {
+        clearHealthPolling();
+        setRestartPhase('idle');
+        throw new Error(e instanceof Error ? e.message : errorMessage);
+      }
+    },
+    [platform, startHealthPolling, clearHealthPolling],
+  );
 
   const handleDownload = async () => {
     setError(null);
@@ -209,24 +229,9 @@ export function GpuPage() {
 
   const handleRestart = async () => {
     setError(null);
-    setRestartPhase('stopping');
     try {
-      setRestartPhase('waiting');
-      startHealthPolling();
-      await platform.lifecycle.restartServer();
-      if (healthPollRef.current) {
-        clearInterval(healthPollRef.current);
-        healthPollRef.current = null;
-      }
-      setRestartPhase('ready');
-      queryClient.invalidateQueries();
-      setTimeout(() => setRestartPhase('idle'), 2000);
+      await restartServerWithPolling('Restart failed');
     } catch (e: unknown) {
-      setRestartPhase('idle');
-      if (healthPollRef.current) {
-        clearInterval(healthPollRef.current);
-        healthPollRef.current = null;
-      }
       setError(e instanceof Error ? e.message : 'Restart failed');
     }
   };
@@ -236,22 +241,8 @@ export function GpuPage() {
     setRestartPhase('stopping');
     try {
       await apiClient.deleteCudaBackend();
-      setRestartPhase('waiting');
-      startHealthPolling();
-      await platform.lifecycle.restartServer();
-      if (healthPollRef.current) {
-        clearInterval(healthPollRef.current);
-        healthPollRef.current = null;
-      }
-      setRestartPhase('ready');
-      queryClient.invalidateQueries();
-      setTimeout(() => setRestartPhase('idle'), 2000);
+      await restartServerWithPolling('Failed to switch to CPU');
     } catch (e: unknown) {
-      setRestartPhase('idle');
-      if (healthPollRef.current) {
-        clearInterval(healthPollRef.current);
-        healthPollRef.current = null;
-      }
       setError(e instanceof Error ? e.message : 'Failed to switch to CPU');
       refetchCudaStatus();
     }

app/src/components/ServerTab/LogsPage.tsx

@@ -96,7 +96,7 @@ export function LogsPage() {
             )}
           </div>
         ) : (
-          entries.map((entry, i) => <LogLine key={`${entry.timestamp}-${i}`} entry={entry} />)
+          entries.map((entry) => <LogLine key={entry.id} entry={entry} />)
         )}
       </div>
     </div>

app/src/components/ServerTab/SettingRow.tsx

@@ -48,7 +48,7 @@ export function SettingRow({
         <div className="min-w-0">
           <label
             htmlFor={htmlFor}
-            className="text-sm font-medium leading-none cursor-pointer select-none"
+            className={`text-sm font-medium leading-none select-none ${htmlFor ? 'cursor-pointer' : ''}`}
           >
             {title}
           </label>

app/src/components/ui/toaster.tsx

@@ -25,7 +25,7 @@ export function Toaster() {
           <ToastClose />
         </Toast>
       ))}
-      <ToastViewport className={isPlayerOpen ? 'sm:bottom-32' : ''} />
+      <ToastViewport className={isPlayerOpen ? 'sm:bottom-44' : ''} />
     </ToastProvider>
   );
 }

app/src/components/ui/toggle.tsx

@@ -26,6 +26,7 @@ const Toggle = React.forwardRef<HTMLButtonElement, ToggleProps>(
         }}
         className={cn(
           'relative inline-flex h-5 w-9 shrink-0 items-center rounded-full transition-colors',
+          'focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2',
           checked ? 'bg-accent' : 'bg-muted-foreground/25',
           disabled ? 'opacity-50 cursor-not-allowed' : 'cursor-pointer',
           className,

app/src/lib/api/client.ts

@@ -32,8 +32,24 @@ import type {
   TranscriptionResponse,
   VoiceProfileCreate,
   VoiceProfileResponse,
+  WhisperModelSize,
 } from './types';
 
+function formatErrorDetail(detail: unknown, fallback: string): string {
+  if (typeof detail === 'string') return detail;
+  if (Array.isArray(detail)) {
+    return detail
+      .map((e: Record<string, unknown>) => e.msg || e.message || JSON.stringify(e))
+      .join('; ');
+  }
+  if (detail && typeof detail === 'object') {
+    const obj = detail as Record<string, unknown>;
+    if (typeof obj.message === 'string') return obj.message;
+    return JSON.stringify(detail);
+  }
+  return fallback;
+}
+
 class ApiClient {
   private getBaseUrl(): string {
     const serverUrl = useServerStore.getState().serverUrl;
@@ -54,7 +70,7 @@ class ApiClient {
       const error = await response.json().catch(() => ({
         detail: response.statusText,
       }));
-      throw new Error(error.detail || `HTTP error! status: ${response.status}`);
+      throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
     }
 
     return response.json();
@@ -113,7 +129,7 @@ class ApiClient {
       const error = await response.json().catch(() => ({
         detail: response.statusText,
       }));
-      throw new Error(error.detail || `HTTP error! status: ${response.status}`);
+      throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
     }
 
     return response.json();
@@ -147,7 +163,7 @@ class ApiClient {
       const error = await response.json().catch(() => ({
         detail: response.statusText,
       }));
-      throw new Error(error.detail || `HTTP error! status: ${response.status}`);
+      throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
     }
 
     return response.blob();
@@ -167,7 +183,7 @@ class ApiClient {
       const error = await response.json().catch(() => ({
         detail: response.statusText,
       }));
-      throw new Error(error.detail || `HTTP error! status: ${response.status}`);
+      throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
     }
 
     return response.json();
@@ -187,7 +203,7 @@ class ApiClient {
       const error = await response.json().catch(() => ({
         detail: response.statusText,
       }));
-      throw new Error(error.detail || `HTTP error! status: ${response.status}`);
+      throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
     }
 
     return response.json();
@@ -257,7 +273,7 @@ class ApiClient {
       const error = await response.json().catch(() => ({
         detail: response.statusText,
       }));
-      throw new Error(error.detail || `HTTP error! status: ${response.status}`);
+      throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
     }
 
     return response.blob();
@@ -271,7 +287,7 @@ class ApiClient {
       const error = await response.json().catch(() => ({
         detail: response.statusText,
       }));
-      throw new Error(error.detail || `HTTP error! status: ${response.status}`);
+      throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
     }
 
     return response.blob();
@@ -297,7 +313,7 @@ class ApiClient {
       const error = await response.json().catch(() => ({
         detail: response.statusText,
       }));
-      throw new Error(error.detail || `HTTP error! status: ${response.status}`);
+      throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
     }
 
     return response.json();
@@ -318,12 +334,19 @@ class ApiClient {
   }
 
   // Transcription
-  async transcribeAudio(file: File, language?: LanguageCode): Promise<TranscriptionResponse> {
+  async transcribeAudio(
+    file: File,
+    language?: LanguageCode,
+    model?: WhisperModelSize,
+  ): Promise<TranscriptionResponse> {
     const formData = new FormData();
     formData.append('file', file);
     if (language) {
       formData.append('language', language);
     }
+    if (model) {
+      formData.append('model', model);
+    }
 
     const url = `${this.getBaseUrl()}/transcribe`;
     const response = await fetch(url, {
@@ -335,7 +358,7 @@ class ApiClient {
       const error = await response.json().catch(() => ({
         detail: response.statusText,
       }));
-      throw new Error(error.detail || `HTTP error! status: ${response.status}`);
+      throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
     }
 
     return response.json();
@@ -608,7 +631,7 @@ class ApiClient {
       const error = await response.json().catch(() => ({
         detail: response.statusText,
       }));
-      throw new Error(error.detail || `HTTP error! status: ${response.status}`);
+      throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
     }
 
     return response.blob();
@@ -705,7 +728,7 @@ class ApiClient {
       const error = await response.json().catch(() => ({
         detail: response.statusText,
       }));
-      throw new Error(error.detail || `HTTP error! status: ${response.status}`);
+      throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
     }
 
     return response.blob();

app/src/lib/api/types.ts

@@ -99,8 +99,11 @@ export interface HistoryListResponse {
   total: number;
 }
 
+export type WhisperModelSize = 'base' | 'small' | 'medium' | 'large' | 'turbo';
+
 export interface TranscriptionRequest {
   language?: LanguageCode;
+  model?: WhisperModelSize;
 }
 
 export interface TranscriptionResponse {

app/src/lib/hooks/useGenerationProgress.ts

@@ -75,8 +75,8 @@ export function useGenerationProgress() {
             currentSources.delete(id);
             removePendingGeneration(id);
 
-            // Refresh history to pick up the completed generation
-            queryClient.invalidateQueries({ queryKey: ['history'] });
+            // Refetch history to pick up the completed generation
+            queryClient.refetchQueries({ queryKey: ['history'] });
 
             // If this generation was queued for a story, add it now
             const storyId = removePendingStoryAdd(id);
@@ -120,7 +120,7 @@ export function useGenerationProgress() {
             removePendingGeneration(id);
             removePendingStoryAdd(id);
 
-            queryClient.invalidateQueries({ queryKey: ['history'] });
+            queryClient.refetchQueries({ queryKey: ['history'] });
 
             toast({
               title: data.status === 'not_found' ? 'Generation not found' : 'Generation failed',
@@ -134,11 +134,12 @@ export function useGenerationProgress() {
       };
 
       source.onerror = () => {
-        // EventSource auto-reconnects, but if we get repeated errors
-        // just clean up
+        // SSE connection dropped — clean up and refresh history so any
+        // completed/failed generation still appears in the list
         source.close();
         currentSources.delete(id);
         removePendingGeneration(id);
+        queryClient.refetchQueries({ queryKey: ['history'] });
       };
 
       currentSources.set(id, source);

app/src/lib/hooks/useTranscription.ts

@@ -1,10 +1,18 @@
 import { useMutation } from '@tanstack/react-query';
 import { apiClient } from '@/lib/api/client';
+import type { WhisperModelSize } from '@/lib/api/types';
 import type { LanguageCode } from '@/lib/constants/languages';
 
 export function useTranscription() {
   return useMutation({
-    mutationFn: ({ file, language }: { file: File; language?: LanguageCode }) =>
-      apiClient.transcribeAudio(file, language),
+    mutationFn: ({
+      file,
+      language,
+      model,
+    }: {
+      file: File;
+      language?: LanguageCode;
+      model?: WhisperModelSize;
+    }) => apiClient.transcribeAudio(file, language, model),
   });
 }

app/src/stores/logStore.ts

@@ -3,7 +3,10 @@ import type { ServerLogEntry } from '@/platform/types';
 
 const MAX_LOG_ENTRIES = 2000;
 
+let nextLogEntryId = 0;
+
 export interface LogEntry extends ServerLogEntry {
+  id: number;
   timestamp: number;
 }
 
@@ -17,9 +20,8 @@ export const useLogStore = create<LogStore>((set) => ({
   entries: [],
   addEntry: (entry) =>
     set((state) => {
-      const newEntry: LogEntry = { ...entry, timestamp: Date.now() };
+      const newEntry: LogEntry = { ...entry, id: nextLogEntryId++, timestamp: Date.now() };
       const entries = [...state.entries, newEntry];
-      // Cap buffer size
       if (entries.length > MAX_LOG_ENTRIES) {
         return { entries: entries.slice(entries.length - MAX_LOG_ENTRIES) };
       }

backend/__init__.py

@@ -1,3 +1,3 @@
 # Backend package
 
-__version__ = "0.2.3"
+__version__ = "0.3.0"

backend/backends/__init__.py

@@ -134,6 +134,7 @@ class STTBackend(Protocol):
         self,
         audio_path: str,
         language: Optional[str] = None,
+        model_size: Optional[str] = None,
     ) -> str:
         """
         Transcribe audio to text.

backend/backends/mlx_backend.py

@@ -345,18 +345,20 @@ class MLXSTTBackend:
         self,
         audio_path: str,
         language: Optional[str] = None,
+        model_size: Optional[str] = None,
     ) -> str:
         """
         Transcribe audio to text.
 
         Args:
             audio_path: Path to audio file
-            language: Optional language hint (en or zh)
+            language: Optional language hint
+            model_size: Optional model size override
 
         Returns:
             Transcribed text
         """
-        await self.load_model_async(None)
+        await self.load_model_async(model_size)
 
         def _transcribe_sync():
             """Run synchronous transcription in thread pool."""

backend/backends/pytorch_backend.py

@@ -306,18 +306,20 @@ class PyTorchSTTBackend:
         self,
         audio_path: str,
         language: Optional[str] = None,
+        model_size: Optional[str] = None,
     ) -> str:
         """
         Transcribe audio to text.
 
         Args:
             audio_path: Path to audio file
-            language: Optional language hint (en or zh)
+            language: Optional language hint
+            model_size: Optional model size override
 
         Returns:
             Transcribed text
         """
-        await self.load_model_async(None)
+        await self.load_model_async(model_size)
 
         def _transcribe_sync():
             """Run synchronous transcription in thread pool."""

backend/models.py

@@ -149,7 +149,8 @@ class HistoryListResponse(BaseModel):
 class TranscriptionRequest(BaseModel):
     """Request model for audio transcription."""
 
-    language: Optional[str] = Field(None, pattern="^(en|zh)$")
+    language: Optional[str] = Field(None, pattern="^(en|zh|ja|ko|de|fr|ru|pt|es|it)$")
+    model: Optional[str] = Field(None, pattern="^(base|small|medium|large|turbo)$")
 
 
 class TranscriptionResponse(BaseModel):

backend/routes/generations.py

@@ -1,12 +1,15 @@
 """TTS generation endpoints."""
 
 import asyncio
+import logging
 import uuid
 
 from fastapi import APIRouter, Depends, HTTPException
 from fastapi.responses import StreamingResponse
 from sqlalchemy.orm import Session
 
+logger = logging.getLogger(__name__)
+
 from .. import models
 from ..services import history, profiles, tts
 from ..database import Generation as DBGeneration, VoiceProfile as DBVoiceProfile, get_db
@@ -181,25 +184,28 @@ async def get_generation_status(generation_id: str, db: Session = Depends(get_db
     import json
 
     async def event_stream():
-        while True:
-            db.expire_all()
-            gen = db.query(DBGeneration).filter_by(id=generation_id).first()
-            if not gen:
-                yield f"data: {json.dumps({'status': 'not_found', 'id': generation_id})}\n\n"
-                return
+        try:
+            while True:
+                db.expire_all()
+                gen = db.query(DBGeneration).filter_by(id=generation_id).first()
+                if not gen:
+                    yield f"data: {json.dumps({'status': 'not_found', 'id': generation_id})}\n\n"
+                    return
 
-            payload = {
-                "id": gen.id,
-                "status": gen.status or "completed",
-                "duration": gen.duration,
-                "error": gen.error,
-            }
-            yield f"data: {json.dumps(payload)}\n\n"
+                payload = {
+                    "id": gen.id,
+                    "status": gen.status or "completed",
+                    "duration": gen.duration,
+                    "error": gen.error,
+                }
+                yield f"data: {json.dumps(payload)}\n\n"
 
-            if (gen.status or "completed") in ("completed", "failed"):
-                return
+                if (gen.status or "completed") in ("completed", "failed"):
+                    return
 
-            await asyncio.sleep(1)
+                await asyncio.sleep(1)
+        except (BrokenPipeError, ConnectionResetError, asyncio.CancelledError):
+            logger.debug("SSE client disconnected for generation %s", generation_id)
 
     return StreamingResponse(
         event_stream(),
@@ -265,9 +271,12 @@ async def stream_speech(
     wav_bytes = tts.audio_to_wav_bytes(audio, sample_rate)
 
     async def _wav_stream():
-        chunk_size = 64 * 1024
-        for i in range(0, len(wav_bytes), chunk_size):
-            yield wav_bytes[i : i + chunk_size]
+        try:
+            chunk_size = 64 * 1024
+            for i in range(0, len(wav_bytes), chunk_size):
+                yield wav_bytes[i : i + chunk_size]
+        except (BrokenPipeError, ConnectionResetError, asyncio.CancelledError):
+            logger.debug("Client disconnected during audio stream")
 
     return StreamingResponse(
         _wav_stream(),

backend/routes/profiles.py

@@ -102,6 +102,10 @@ async def delete_profile(
     return {"message": "Profile deleted successfully"}
 
 
+SAMPLE_MAX_FILE_SIZE = 50 * 1024 * 1024  # 50 MB
+SAMPLE_UPLOAD_CHUNK_SIZE = 1024 * 1024  # 1 MB
+
+
 @router.post("/profiles/{profile_id}/samples", response_model=models.ProfileSampleResponse)
 async def add_profile_sample(
     profile_id: str,
@@ -115,8 +119,16 @@ async def add_profile_sample(
     file_suffix = _uploaded_ext if _uploaded_ext in _allowed_audio_exts else ".wav"
 
     with tempfile.NamedTemporaryFile(suffix=file_suffix, delete=False) as tmp:
-        content = await file.read()
-        tmp.write(content)
+        total_size = 0
+        while chunk := await file.read(SAMPLE_UPLOAD_CHUNK_SIZE):
+            total_size += len(chunk)
+            if total_size > SAMPLE_MAX_FILE_SIZE:
+                Path(tmp.name).unlink(missing_ok=True)
+                raise HTTPException(
+                    status_code=413,
+                    detail=f"File too large (max {SAMPLE_MAX_FILE_SIZE // (1024 * 1024)} MB)",
+                )
+            tmp.write(chunk)
         tmp_path = tmp.name
 
     try:

backend/routes/transcription.py

@@ -20,6 +20,7 @@ UPLOAD_CHUNK_SIZE = 1024 * 1024  # 1MB
 async def transcribe_audio(
     file: UploadFile = File(...),
     language: str | None = Form(None),
+    model: str | None = Form(None),
 ):
     """Transcribe audio file to text."""
     with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp:
@@ -29,14 +30,23 @@ async def transcribe_audio(
 
     try:
         from ..utils.audio import load_audio
+        from ..backends import WHISPER_HF_REPOS
 
         audio, sr = await asyncio.to_thread(load_audio, tmp_path)
         duration = len(audio) / sr
 
         whisper_model = transcribe.get_whisper_model()
-        model_size = whisper_model.model_size
+        model_size = model if model else whisper_model.model_size
 
-        if not whisper_model.is_loaded() and not whisper_model._is_model_cached(model_size):
+        valid_sizes = list(WHISPER_HF_REPOS.keys())
+        if model_size not in valid_sizes:
+            raise HTTPException(
+                status_code=400,
+                detail=f"Invalid model size '{model_size}'. Must be one of: {', '.join(valid_sizes)}",
+            )
+
+        already_loaded = whisper_model.is_loaded() and whisper_model.model_size == model_size
+        if not already_loaded and not whisper_model._is_model_cached(model_size):
             progress_model_name = f"whisper-{model_size}"
             task_manager = get_task_manager()
 
@@ -59,7 +69,7 @@ async def transcribe_audio(
                 },
             )
 
-        text = await whisper_model.transcribe(tmp_path, language)
+        text = await whisper_model.transcribe(tmp_path, language, model_size)
 
         return models.TranscriptionResponse(
             text=text,

backend/services/profiles.py

@@ -22,7 +22,7 @@ from ..database import (
     Generation as DBGeneration,
 )
 from ..models import EffectConfig
-from ..utils.audio import validate_reference_audio, load_audio, save_audio
+from ..utils.audio import validate_reference_audio, validate_and_load_reference_audio, load_audio, save_audio
 from ..utils.images import validate_image, process_avatar
 from ..utils.cache import _get_cache_dir, clear_profile_cache
 from .tts import get_tts_model
@@ -117,11 +117,16 @@ async def add_profile_sample(
     Returns:
         Created sample
     """
+    import asyncio
+
     profile = db.query(DBVoiceProfile).filter_by(id=profile_id).first()
     if not profile:
         raise ValueError(f"Profile {profile_id} not found")
 
-    is_valid, error_msg = validate_reference_audio(audio_path)
+    # Validate and load audio in a single pass, off the event loop
+    is_valid, error_msg, audio, sr = await asyncio.to_thread(
+        validate_and_load_reference_audio, audio_path
+    )
     if not is_valid:
         raise ValueError(f"Invalid reference audio: {error_msg}")
 
@@ -130,8 +135,7 @@ async def add_profile_sample(
     profile_dir.mkdir(parents=True, exist_ok=True)
 
     dest_path = profile_dir / f"{sample_id}.wav"
-    audio, sr = load_audio(audio_path)
-    save_audio(audio, str(dest_path), sr)
+    await asyncio.to_thread(save_audio, audio, str(dest_path), sr)
 
     db_sample = DBProfileSample(
         id=sample_id,

backend/utils/audio.py

@@ -217,22 +217,40 @@ def validate_reference_audio(
     Returns:
         Tuple of (is_valid, error_message)
     """
+    result = validate_and_load_reference_audio(
+        audio_path, min_duration, max_duration, min_rms
+    )
+    return (result[0], result[1])
+
+
+def validate_and_load_reference_audio(
+    audio_path: str,
+    min_duration: float = 2.0,
+    max_duration: float = 30.0,
+    min_rms: float = 0.01,
+) -> Tuple[bool, Optional[str], Optional[np.ndarray], Optional[int]]:
+    """
+    Validate and load reference audio in a single pass.
+    
+    Returns:
+        Tuple of (is_valid, error_message, audio_array, sample_rate)
+    """
     try:
         audio, sr = load_audio(audio_path)
         duration = len(audio) / sr
         
         if duration < min_duration:
-            return False, f"Audio too short (minimum {min_duration} seconds)"
+            return False, f"Audio too short (minimum {min_duration} seconds)", None, None
         if duration > max_duration:
-            return False, f"Audio too long (maximum {max_duration} seconds)"
+            return False, f"Audio too long (maximum {max_duration} seconds)", None, None
         
         rms = np.sqrt(np.mean(audio**2))
         if rms < min_rms:
-            return False, "Audio is too quiet or silent"
+            return False, "Audio is too quiet or silent", None, None
         
         if np.abs(audio).max() > 0.99:
-            return False, "Audio is clipping (reduce input gain)"
+            return False, "Audio is clipping (reduce input gain)", None, None
         
-        return True, None
+        return True, None, audio, sr
     except Exception as e:
-        return False, f"Error validating audio: {str(e)}"
+        return False, f"Error validating audio: {str(e)}", None, None

backend/utils/progress.py

@@ -246,6 +246,8 @@ class ProgressManager:
                     # Send heartbeat
                     yield ": heartbeat\n\n"
                     continue
+        except (BrokenPipeError, ConnectionResetError, asyncio.CancelledError):
+            logger.debug(f"SSE client disconnected from {model_name}")
         finally:
             # Remove from listeners
             if model_name in self._listeners:

landing/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@voicebox/landing",
-  "version": "0.2.3",
+  "version": "0.3.0",
   "description": "Landing page for voicebox.sh",
   "scripts": {
     "dev": "bun --bun next dev --turbo",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "voicebox",
-  "version": "0.2.3",
+  "version": "0.3.0",
   "private": true,
   "workspaces": [
     "app",

tauri/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@voicebox/tauri",
   "private": true,
-  "version": "0.2.3",
+  "version": "0.3.0",
   "type": "module",
   "scripts": {
     "dev": "vite",

tauri/src-tauri/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "voicebox"
-version = "0.2.3"
+version = "0.3.0"
 description = "A production-quality desktop app for Qwen3-TTS voice cloning and generation"
 authors = ["you"]
 license = ""

tauri/src-tauri/build.rs

@@ -23,15 +23,15 @@ fn main() {
         }
     }
 
+    let project_root = env!("CARGO_MANIFEST_DIR");
+    let gen_dir = format!("{}/gen", project_root);
+    std::fs::create_dir_all(&gen_dir).expect("Failed to create gen directory");
+
     // Compile macOS Liquid Glass icon
     #[cfg(target_os = "macos")]
     {
-        let project_root = env!("CARGO_MANIFEST_DIR");
         // voicebox.icon is in tauri/assets/voicebox.icon (one level up from src-tauri)
         let icon_source = format!("{}/../assets/voicebox.icon", project_root);
-        let gen_dir = format!("{}/gen", project_root);
-
-        std::fs::create_dir_all(&gen_dir).expect("Failed to create gen directory");
 
         if std::path::Path::new(&icon_source).exists() {
             println!("cargo:rerun-if-changed={}", icon_source);
@@ -76,6 +76,71 @@ fn main() {
                     panic!("Icon compilation failed");
                 }
             }
+
+            // Generate voicebox.icns from the source PNG via sips + iconutil
+            let icns_path = format!("{}/voicebox.icns", gen_dir);
+            if !std::path::Path::new(&icns_path).exists() {
+                let source_png = format!("{}/Assets/Voicebox.png", icon_source);
+                if std::path::Path::new(&source_png).exists() {
+                    let iconset_dir = format!("{}/voicebox.iconset", gen_dir);
+                    std::fs::create_dir_all(&iconset_dir).ok();
+
+                    let sizes: &[(u32, &str)] = &[
+                        (16, "icon_16x16.png"),
+                        (32, "[email protected]"),
+                        (32, "icon_32x32.png"),
+                        (64, "[email protected]"),
+                        (128, "icon_128x128.png"),
+                        (256, "[email protected]"),
+                        (256, "icon_256x256.png"),
+                        (512, "[email protected]"),
+                        (512, "icon_512x512.png"),
+                        (1024, "[email protected]"),
+                    ];
+
+                    for (size, name) in sizes {
+                        let dest = format!("{}/{}", iconset_dir, name);
+                        let status = Command::new("sips")
+                            .args([
+                                "-z",
+                                &size.to_string(),
+                                &size.to_string(),
+                                &source_png,
+                                "--out",
+                                &dest,
+                            ])
+                            .output();
+                        if let Ok(out) = status {
+                            if !out.status.success() {
+                                eprintln!(
+                                    "sips failed for {}: {}",
+                                    name,
+                                    String::from_utf8_lossy(&out.stderr)
+                                );
+                            }
+                        }
+                    }
+
+                    let iconutil_output = Command::new("iconutil")
+                        .args(["-c", "icns", "-o", &icns_path, &iconset_dir])
+                        .output();
+
+                    match iconutil_output {
+                        Ok(out) if out.status.success() => {
+                            println!("Generated voicebox.icns");
+                        }
+                        Ok(out) => {
+                            eprintln!("iconutil failed: {}", String::from_utf8_lossy(&out.stderr));
+                        }
+                        Err(e) => {
+                            eprintln!("Failed to run iconutil: {}", e);
+                        }
+                    }
+
+                    // Clean up iconset directory
+                    std::fs::remove_dir_all(&iconset_dir).ok();
+                }
+            }
         } else {
             println!(
                 "cargo:warning=Icon source not found at {}, skipping icon compilation",
@@ -84,5 +149,18 @@ fn main() {
         }
     }
 
+    // Ensure all resource files exist so Tauri's bundler doesn't fail.
+    // On non-macOS these are always stubs. On macOS, actool may not produce
+    // Assets.car if the Xcode version doesn't support the .icon format.
+    {
+        let required = ["Assets.car", "voicebox.icns", "partial.plist"];
+        for name in required {
+            let path = format!("{}/{}", gen_dir, name);
+            if !std::path::Path::new(&path).exists() {
+                std::fs::write(&path, b"").ok();
+            }
+        }
+    }
+
     tauri_build::build()
 }

tauri/src-tauri/tauri.conf.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://schema.tauri.app/config/2",
   "productName": "Voicebox",
-  "version": "0.2.3",
+  "version": "0.3.0",
   "identifier": "sh.voicebox.app",
   "build": {
     "beforeDevCommand": "bun run dev",

tauri/src/platform/lifecycle.ts

@@ -88,16 +88,27 @@ class TauriLifecycle implements PlatformLifecycle {
   }
 
   subscribeToServerLogs(callback: (entry: ServerLogEntry) => void): () => void {
+    let disposed = false;
     let unlisten: (() => void) | null = null;
 
-    listen<ServerLogEntry>('server-log', (event) => {
+    void listen<ServerLogEntry>('server-log', (event) => {
       callback(event.payload);
-    }).then((fn) => {
-      unlisten = fn;
-    });
+    })
+      .then((fn) => {
+        if (disposed) {
+          fn();
+          return;
+        }
+        unlisten = fn;
+      })
+      .catch((error) => {
+        console.error('Failed to subscribe to server logs:', error);
+      });
 
     return () => {
+      disposed = true;
       unlisten?.();
+      unlisten = null;
     };
   }
 }

web/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@voicebox/web",
   "private": true,
-  "version": "0.2.3",
+  "version": "0.3.0",
   "type": "module",
   "scripts": {
     "dev": "vite",