Files
TalkEdit/frontend/src/App.tsx
2026-04-08 01:42:00 -06:00

515 lines
20 KiB
TypeScript

import { useEffect, useState, useRef } from 'react';
import { useEditorStore } from './store/editorStore';
import VideoPlayer from './components/VideoPlayer';
import TranscriptEditor from './components/TranscriptEditor';
import WaveformTimeline from './components/WaveformTimeline';
import AIPanel from './components/AIPanel';
import ExportDialog from './components/ExportDialog';
import SettingsPanel from './components/SettingsPanel';
import DevPanel from './components/DevPanel';
import SilenceTrimmerPanel from './components/SilenceTrimmerPanel';
import { useKeyboardShortcuts } from './hooks/useKeyboardShortcuts';
import {
Film,
FolderOpen,
Settings,
Sparkles,
Download,
FolderSearch,
FileInput,
Save,
Scissors,
VolumeX,
} from 'lucide-react';
const IS_DESKTOP = !!window.desktopAPI;
type Panel = 'ai' | 'settings' | 'export' | 'silence' | null;
export default function App() {
const {
videoPath,
words,
isTranscribing,
transcriptionProgress,
transcriptionStatus,
loadVideo,
setBackendUrl,
setTranscription,
setTranscribing,
backendUrl,
selectedWordIndices,
addCutRange,
addMuteRange,
} = useEditorStore();
const [activePanel, setActivePanel] = useState<Panel>(null);
const [manualPath, setManualPath] = useState('');
const [whisperModel, setWhisperModel] = useState('base');
const [cutMode, setCutMode] = useState(false);
const [muteMode, setMuteMode] = useState(false);
const fileInputRef = useRef<HTMLInputElement>(null);
const lastVideoPathRef = useRef<string | null>(null);
useKeyboardShortcuts();
// Handle Escape key to exit cut/mute modes
useEffect(() => {
const handleKeyDown = (e: KeyboardEvent) => {
if (e.key === 'Escape') {
setCutMode(false);
setMuteMode(false);
}
};
window.addEventListener('keydown', handleKeyDown);
return () => window.removeEventListener('keydown', handleKeyDown);
}, []);
useEffect(() => {
if (IS_DESKTOP) {
window.desktopAPI!.getBackendUrl().then(setBackendUrl);
}
// In Tauri on Linux/WebKit2GTK the ipc:// custom protocol is blocked by
// WebKit internals; postMessage fallback works but logs noisy warnings.
// The backend URL is fixed at 127.0.0.1:8000 so we rely on the store default.
}, [setBackendUrl]);
useEffect(() => {
if (!import.meta.env.DEV) return;
const previousVideoPath = lastVideoPathRef.current;
if (previousVideoPath !== videoPath) {
console.log('[app-state] videoPath transition', {
from: previousVideoPath,
to: videoPath,
wordCount: words.length,
isTranscribing,
});
if (previousVideoPath && !videoPath) {
console.warn('[app-state] videoPath cleared and UI will show welcome screen', {
previousVideoPath,
wordCount: words.length,
isTranscribing,
});
}
lastVideoPathRef.current = videoPath;
}
}, [videoPath, words.length, isTranscribing]);
const handleLoadProject = async () => {
if (!IS_DESKTOP) return;
try {
if (import.meta.env.DEV) console.log('[app-action] loadProject:dialogOpen');
const projectPath = await window.desktopAPI!.openProject();
if (import.meta.env.DEV) console.log('[app-action] loadProject:dialogResult', { projectPath });
if (!projectPath) return;
const content = await window.desktopAPI!.readFile(projectPath);
const data = JSON.parse(content);
if (import.meta.env.DEV) {
console.log('[app-action] loadProject:parsed', {
projectPath,
videoPath: data?.videoPath,
words: Array.isArray(data?.words) ? data.words.length : null,
segments: Array.isArray(data?.segments) ? data.segments.length : null,
});
}
useEditorStore.getState().loadProject(data);
} catch (err) {
console.error('Failed to load project:', err);
alert(`Failed to load project: ${err}`);
}
};
const handleSaveProject = async () => {
if (!IS_DESKTOP) return;
try {
const savePath = await window.desktopAPI!.saveProject();
if (!savePath) return;
const data = useEditorStore.getState().saveProject();
const path = savePath.endsWith('.aive') ? savePath : `${savePath}.aive`;
await window.desktopAPI!.writeFile(path, JSON.stringify(data, null, 2));
} catch (err) {
console.error('Failed to save project:', err);
alert(`Failed to save project: ${err}`);
}
};
const handleOpenFile = async () => {
if (IS_DESKTOP) {
if (import.meta.env.DEV) console.log('[app-action] openFile:dialogOpen');
const path = await window.desktopAPI!.openFile();
if (import.meta.env.DEV) console.log('[app-action] openFile:dialogResult', { path });
if (path) {
if (import.meta.env.DEV) console.log('[app-action] openFile:loadVideo', { path });
loadVideo(path);
await transcribeVideo(path);
}
} else {
// Browser: use the manual path input
const path = manualPath.trim();
if (path) {
if (import.meta.env.DEV) console.log('[app-action] openFile:webManualPath', { path });
loadVideo(path);
await transcribeVideo(path);
}
}
};
const handleManualSubmit = async (e: React.FormEvent) => {
e.preventDefault();
const path = manualPath.trim();
if (!path) return;
if (import.meta.env.DEV) console.log('[app-action] manualSubmit:loadVideo', { path });
loadVideo(path);
await transcribeVideo(path);
};
const transcribeVideo = async (path: string) => {
if (import.meta.env.DEV) console.log('[app-action] transcribe:start', { path, whisperModel });
setTranscribing(true, 0, 'Checking model...');
try {
if (!window.desktopAPI?.transcribe) {
throw new Error('Transcription not available');
}
// Step 1: ensure model is downloaded (may take a while on first run)
const MODEL_SIZES: Record<string, string> = {
'tiny': '~75 MB',
'tiny.en': '~75 MB',
'base': '~140 MB',
'base.en': '~140 MB',
'small': '~460 MB',
'small.en': '~460 MB',
'medium': '~1.5 GB',
'medium.en': '~1.5 GB',
'large': '~2.9 GB',
'large-v2': '~2.9 GB',
'large-v3': '~2.9 GB',
'large-v3-turbo': '~1.6 GB',
'distil-large-v3': '~1.5 GB',
'distil-medium.en': '~750 MB',
'distil-small.en': '~190 MB',
};
const modelLabel = MODEL_SIZES[whisperModel] ?? 'unknown size';
setTranscribing(true, 5, `Downloading ${whisperModel} model (${modelLabel})...`);
await window.desktopAPI.ensureModel(whisperModel);
if (import.meta.env.DEV) console.log('[app-action] transcribe:modelReady', { whisperModel });
// Step 2: run transcription
setTranscribing(true, 20, 'Transcribing audio...');
const data = await window.desktopAPI.transcribe(path, whisperModel);
if (import.meta.env.DEV) {
console.log('[app-action] transcribe:result', {
path,
words: Array.isArray(data?.words) ? data.words.length : null,
segments: Array.isArray(data?.segments) ? data.segments.length : null,
language: data?.language,
});
}
setTranscription(data);
} catch (err) {
console.error('Transcription error:', err);
alert(`Transcription failed. Check the console for details.\n\n${err}`);
} finally {
if (import.meta.env.DEV) console.log('[app-action] transcribe:finish', { path });
setTranscribing(false);
}
};
const togglePanel = (panel: Panel) => {
setActivePanel((prev) => (prev === panel ? null : panel));
};
const handleCut = () => {
if (selectedWordIndices.length > 0) {
// If words are selected, apply cut immediately
const sorted = [...selectedWordIndices].sort((a, b) => a - b);
const startTime = words[sorted[0]].start;
const endTime = words[sorted[sorted.length - 1]].end;
addCutRange(startTime, endTime);
} else {
// Toggle cut mode
setCutMode(!cutMode);
setMuteMode(false); // Exit mute mode
}
};
const handleMute = () => {
if (selectedWordIndices.length > 0) {
// If words are selected, apply mute immediately
const sorted = [...selectedWordIndices].sort((a, b) => a - b);
const startTime = words[sorted[0]].start;
const endTime = words[sorted[sorted.length - 1]].end;
addMuteRange(startTime, endTime);
} else {
// Toggle mute mode
setMuteMode(!muteMode);
setCutMode(false); // Exit cut mode
}
};
if (!videoPath) {
return (
<div className="h-screen flex flex-col items-center justify-center gap-8 bg-editor-bg px-6">
<div className="flex flex-col items-center gap-3">
<Film className="w-14 h-14 text-editor-accent opacity-80" />
<h1 className="text-3xl font-semibold tracking-tight">TalkEdit</h1>
<p className="text-editor-text-muted text-sm max-w-sm text-center">
Offline AI-powered video editor.
</p>
</div>
{/* Whisper model selector */}
<div className="flex items-center gap-3">
<label className="text-xs text-editor-text-muted whitespace-nowrap">Model:</label>
<select
value={whisperModel}
onChange={(e) => setWhisperModel(e.target.value)}
className="px-3 py-1.5 bg-editor-surface border border-editor-border rounded-lg text-xs text-black focus:outline-none focus:border-editor-accent"
>
<optgroup label="Multilingual (any language)">
<option value="tiny">tiny ~75 MB · fastest, low accuracy</option>
<option value="base">base ~140 MB · fast, decent accuracy</option>
<option value="small">small ~460 MB · good balance</option>
<option value="medium">medium ~1.5 GB · better accuracy</option>
<option value="large-v2">large-v2 ~2.9 GB · high accuracy</option>
<option value="large-v3">large-v3 ~2.9 GB · best overall </option>
<option value="large-v3-turbo">large-v3-turbo ~1.6 GB · fast + accurate </option>
<option value="distil-large-v3">distil-large-v3 ~1.5 GB · fast, near large-v3 quality</option>
</optgroup>
<optgroup label="English-only (faster &amp; more accurate for English)">
<option value="tiny.en">tiny.en ~75 MB · fastest English</option>
<option value="base.en">base.en ~140 MB · fast English</option>
<option value="small.en">small.en ~460 MB · good English</option>
<option value="medium.en">medium.en ~1.5 GB · great English</option>
<option value="distil-small.en">distil-small.en ~190 MB · fast English </option>
<option value="distil-medium.en">distil-medium.en ~750 MB · best fast English </option>
</optgroup>
</select>
</div>
<p className="text-[11px] text-editor-text-muted text-center max-w-sm">
For noisy/YouTube videos use <span className="text-white">large-v3</span> or <span className="text-white">large-v3-turbo</span>.
English-only models are ~10% faster and more accurate for English content.
</p>
{IS_DESKTOP ? (
<div className="flex flex-col items-center gap-3">
<button
onClick={handleOpenFile}
className="flex items-center gap-2 px-6 py-3 bg-editor-accent hover:bg-editor-accent-hover rounded-lg text-white font-medium transition-colors"
>
<FolderOpen className="w-5 h-5" />
Open Video File
</button>
<button
onClick={handleLoadProject}
className="flex items-center gap-2 px-4 py-2 text-sm text-editor-text-muted hover:text-editor-text hover:bg-editor-surface rounded-lg transition-colors"
>
<FileInput className="w-4 h-4" />
Load Project (.aive)
</button>
</div>
) : (
/* Browser: manual path input */
<div className="w-full max-w-lg space-y-3">
<div className="flex items-center gap-2 px-3 py-1.5 bg-editor-warning/10 border border-editor-warning/30 rounded-lg">
<span className="text-editor-warning text-xs">
Running in browser paste the full path to your video file below.
</span>
</div>
<form onSubmit={handleManualSubmit} className="flex gap-2">
<div className="flex-1 relative">
<FolderSearch className="absolute left-3 top-1/2 -translate-y-1/2 w-4 h-4 text-editor-text-muted pointer-events-none" />
<input
ref={fileInputRef}
type="text"
value={manualPath}
onChange={(e) => setManualPath(e.target.value)}
placeholder="C:\Videos\my-video.mp4"
className="w-full pl-9 pr-3 py-2.5 bg-editor-surface border border-editor-border rounded-lg text-sm text-editor-text placeholder:text-editor-text-muted/40 focus:outline-none focus:border-editor-accent"
autoFocus
/>
</div>
<button
type="submit"
disabled={!manualPath.trim()}
className="flex items-center gap-2 px-5 py-2.5 bg-editor-accent hover:bg-editor-accent-hover disabled:opacity-40 rounded-lg text-sm text-white font-medium transition-colors whitespace-nowrap"
>
<Film className="w-4 h-4" />
Load &amp; Transcribe
</button>
</form>
<p className="text-[11px] text-editor-text-muted text-center">
Supported: MP4, AVI, MOV, MKV, WebM, M4A
</p>
</div>
)}
</div>
);
}
return (
<div className="h-screen flex flex-col bg-editor-bg overflow-hidden">
{/* Top bar */}
<header className="h-12 flex items-center justify-between px-4 border-b border-editor-border shrink-0">
<div className="flex items-center gap-3">
<Film className="w-5 h-5 text-editor-accent" />
<span className="text-sm font-medium truncate max-w-[300px]">
{videoPath.split(/[\\/]/).pop()}
</span>
</div>
<div className="flex items-center gap-1">
<ToolbarButton
icon={<FolderOpen className="w-4 h-4" />}
label="Open"
onClick={IS_DESKTOP ? handleOpenFile : () => useEditorStore.getState().reset()}
/>
{IS_DESKTOP && (
<ToolbarButton
icon={<Save className="w-4 h-4" />}
label="Save"
onClick={handleSaveProject}
disabled={words.length === 0}
/>
)}
{IS_DESKTOP && (
<ToolbarButton
icon={<FileInput className="w-4 h-4" />}
label="Load"
onClick={handleLoadProject}
/>
)}
<ToolbarButton
icon={<Scissors className="w-4 h-4" />}
label="Cut"
onClick={handleCut}
active={cutMode}
/>
<ToolbarButton
icon={<VolumeX className="w-4 h-4" />}
label="Mute"
onClick={handleMute}
active={muteMode}
/>
<ToolbarButton
icon={<span className="text-[10px] font-semibold">ST</span>}
label="Silence Trim"
active={activePanel === 'silence'}
onClick={() => togglePanel('silence')}
disabled={!videoPath}
/>
<ToolbarButton
icon={<Sparkles className="w-4 h-4" />}
label="AI"
active={activePanel === 'ai'}
onClick={() => togglePanel('ai')}
disabled={words.length === 0}
/>
<ToolbarButton
icon={<Download className="w-4 h-4" />}
label="Export"
active={activePanel === 'export'}
onClick={() => togglePanel('export')}
disabled={words.length === 0}
/>
<ToolbarButton
icon={<Settings className="w-4 h-4" />}
label="Settings"
active={activePanel === 'settings'}
onClick={() => togglePanel('settings')}
/>
</div>
</header>
{/* Main content */}
<div className="flex-1 flex overflow-hidden">
{/* Left: video + transcript */}
<div className="flex-1 flex flex-col min-w-0">
<div className="flex-1 flex min-h-0">
{/* Video player */}
<div className="w-1/2 p-3 flex items-center justify-center bg-black/20">
<VideoPlayer />
</div>
{/* Transcript */}
<div className="w-1/2 border-l border-editor-border flex flex-col min-h-0">
{isTranscribing ? (
<div className="flex-1 flex flex-col items-center justify-center gap-5">
{/* Animated waveform */}
<div className="flex items-end gap-[3px] h-10">
{[35, 60, 45, 80, 55, 70, 40, 65, 50, 75, 40, 58].map((h, i) => (
<div
key={i}
className="w-[5px] rounded-full bg-editor-accent wave-bar"
style={{
height: `${h}%`,
animationDelay: `${i * 75}ms`,
}}
/>
))}
</div>
<div className="text-center space-y-1">
<p className="text-sm font-medium text-editor-text">Processing audio</p>
<p className="text-xs text-editor-text-muted">{transcriptionStatus || 'Please wait...'}</p>
</div>
</div>
) : words.length > 0 ? (
<TranscriptEditor />
) : (
<div className="flex-1 flex items-center justify-center text-editor-text-muted text-sm">
No transcript yet
</div>
)}
</div>
</div>
{/* Waveform timeline */}
<div className="h-32 border-t border-editor-border shrink-0">
<WaveformTimeline cutMode={cutMode} muteMode={muteMode} />
</div>
</div>
{/* Right panel (AI / Export / Settings) */}
{activePanel && (
<div className="w-80 border-l border-editor-border overflow-y-auto shrink-0">
{activePanel === 'silence' && <SilenceTrimmerPanel />}
{activePanel === 'ai' && <AIPanel />}
{activePanel === 'export' && <ExportDialog />}
{activePanel === 'settings' && <SettingsPanel />}
</div>
)}
</div>
{import.meta.env.DEV && <DevPanel />}
</div>
);
}
function ToolbarButton({
icon,
label,
active,
onClick,
disabled,
}: {
icon: React.ReactNode;
label: string;
active?: boolean;
onClick: () => void;
disabled?: boolean;
}) {
return (
<button
onClick={onClick}
disabled={disabled}
title={label}
className={`flex items-center gap-1.5 px-3 py-1.5 rounded-md text-xs font-medium transition-colors ${
active
? 'bg-editor-accent text-white'
: 'text-editor-text-muted hover:text-editor-text hover:bg-editor-surface'
} ${disabled ? 'opacity-40 cursor-not-allowed' : ''}`}
>
{icon}
{label}
</button>
);
}