chore: stage all pending work — caption styling, media server, processing modal, docs, summaries

Includes: - Extended caption styling (font, shadow, dimmed color, bg toggle) - Media server, subtitle downloader, VTT parser, processing modal - Waveform tiers, thumbnail/timeline improvements, transport controls - Hybrid download model, dependency management, clip export enhancements - 21 chat summaries, 2 implementation plans, 2 design specs Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-22 10:48:16 -04:00
parent fd05ae19b5
commit 8ad2f1c800
57 changed files with 4929 additions and 210 deletions
--- a/src/lib/bindings/dependencies.ts
+++ b/src/lib/bindings/dependencies.ts
@@ -27,6 +27,10 @@ export async function checkDependencies(
  return invoke<DependencyStatus[]>('check_dependencies', { cookieSource });
 }

+export async function checkSubtitlesFilterAvailable(): Promise<boolean> {
+  return invoke<boolean>('check_subtitles_filter_available');
+}
+
 export async function installDependency(
  name: string,
  onOutput: (line: string) => void,
--- a/src/lib/bindings/video.ts
+++ b/src/lib/bindings/video.ts
@@ -8,6 +8,8 @@ export interface VideoMetadata {
  fps: number;
  thumbnailUrl: string | null;
  streamUrl: string;
+  hasCaptions: boolean;
+  captionsAreAuto: boolean;
 }

 type DownloadEvent =
@@ -16,6 +18,17 @@ type DownloadEvent =
  | { event: 'finished'; data: { success: boolean; path: string } }
  | { event: 'error'; data: { message: string } };

+export async function getMediaServerPort(): Promise<number> {
+  return invoke<number>('get_media_server_port');
+}
+
+export async function checkCachedDownload(
+  title: string,
+  variant: string
+): Promise<string | null> {
+  return invoke<string | null>('check_cached_download', { title, variant });
+}
+
 export async function resolveUrl(url: string): Promise<VideoMetadata> {
  return invoke<VideoMetadata>('resolve_url', {
    url,
@@ -23,8 +36,21 @@ export async function resolveUrl(url: string): Promise<VideoMetadata> {
  });
 }

+export async function downloadSubtitles(
+  url: string,
+  isAuto: boolean
+): Promise<string> {
+  return invoke<string>('download_subtitles', {
+    url,
+    cookieSource: preferences.cookieSource,
+    isAuto,
+  });
+}
+
 export async function startDownload(
  url: string,
+  formatSpec: string,
+  variant: string,
  onProgress: (percent: number) => void,
  onFilePath: (path: string) => void,
  onFinished: (success: boolean, path: string) => void,
@@ -54,6 +80,8 @@ export async function startDownload(
  await invoke('start_download', {
    url,
    cookieSource: preferences.cookieSource,
+    formatSpec,
+    variant,
    onEvent,
  });
 }
--- a/src/lib/components/ClipList.svelte
+++ b/src/lib/components/ClipList.svelte
@@ -33,9 +33,17 @@
  function handleLabelEdit(clipId: string, value: string) {
    updateClip(clipId, { label: value });
  }
+
+  function handleContainerClick(e: MouseEvent) {
+    const target = e.target as HTMLElement;
+    // Only deselect if the click landed on the container itself, not a child
+    if (target.classList.contains('clip-list')) {
+      selectClip(null);
+    }
+  }
 </script>

-<div class="clip-list">
+<div class="clip-list" role="listbox" onclick={handleContainerClick}>
  {#if clips.length === 0}
    <div class="empty">No clips yet — press I to mark in-point, O to mark out-point</div>
  {:else}
@@ -46,7 +54,8 @@
      <div
        class="clip-row"
        class:selected={clip.id === selectedId}
-        role="button"
+        role="option"
+        aria-selected={clip.id === selectedId}
        tabindex="0"
        onclick={() => handleSelect(clip.id)}
        onkeydown={(e) => {
@@ -91,11 +100,14 @@
        >✕</button>
      </div>
    {/each}
-    {#if onExport}
-      <div class="export-buttons">
+    <div class="action-buttons">
+      {#if selectedId}
+        <button type="button" class="deselect-btn" onclick={() => selectClip(null)}>Deselect</button>
+      {/if}
+      {#if onExport}
        <button type="button" onclick={() => onExport()}>Export All</button>
-      </div>
-    {/if}
+      {/if}
+    </div>
  {/if}
 </div>

@@ -103,10 +115,11 @@
  .clip-list {
    padding: 8px 12px;
    background: var(--bg-secondary);
-    min-height: 60px;
-    max-height: 200px;
+    height: 100%;
+    min-height: 40px;
    overflow-y: auto;
    border-top: 1px solid var(--border);
+    box-sizing: border-box;
  }

  .empty {
@@ -123,17 +136,24 @@
    margin-bottom: 4px;
  }

-  .export-buttons {
+  .action-buttons {
    margin-top: 8px;
    padding-top: 8px;
    border-top: 1px solid var(--border);
+    display: flex;
+    gap: 8px;
  }

-  .export-buttons button {
+  .action-buttons button {
    font-size: 13px;
    padding: 6px 12px;
  }

+  .deselect-btn {
+    color: var(--text-secondary);
+    background: var(--bg-tertiary);
+  }
+
  .clip-row {
    display: flex;
    align-items: center;
--- a/src/lib/components/ProcessingModal.svelte
+++ b/src/lib/components/ProcessingModal.svelte
@@ -0,0 +1,183 @@
+<script lang="ts">
+  import { session, type ProcessingStep } from '$lib/stores/videoSession.svelte';
+
+  const STEP_LABELS: Record<ProcessingStep, string> = {
+    idle: '',
+    downloading: 'Downloading preview…',
+    waveform: 'Generating waveform…',
+    keyframes: 'Extracting keyframes…',
+    thumbnails: 'Generating thumbnails…',
+    captions: 'Downloading captions…',
+    done: 'Ready!',
+  };
+
+  const STEP_ORDER: ProcessingStep[] = [
+    'downloading',
+    'waveform',
+    'keyframes',
+    'thumbnails',
+    'captions',
+    'done',
+  ];
+
+  let currentStepIndex = $derived(STEP_ORDER.indexOf(session.processingStep));
+
+  // Pick progress source based on current step
+  let stepProgress = $derived(() => {
+    switch (session.processingStep) {
+      case 'downloading':
+        return session.previewProgress;
+      case 'waveform':
+      case 'keyframes':
+      case 'thumbnails':
+      case 'captions':
+        return session.processingProgress;
+      case 'done':
+        return 1;
+      default:
+        return 0;
+    }
+  });
+
+  let progressPercent = $derived(Math.round(stepProgress() * 100));
+  let showProgressBar = $derived(
+    session.processingStep !== 'idle' && session.processingStep !== 'done'
+  );
+</script>
+
+<div class="modal-overlay">
+  <div class="modal">
+    <h2>Processing Video</h2>
+    <p class="title">{session.title}</p>
+
+    <div class="steps">
+      {#each STEP_ORDER as step, i}
+        {@const stepLabel = STEP_LABELS[step]}
+        {@const isDone = i < currentStepIndex}
+        {@const isCurrent = step === session.processingStep}
+        <div class="step" class:done={isDone} class:current={isCurrent}>
+          <span class="icon">
+            {#if isDone}
+              ✓
+            {:else if isCurrent}
+              ⏳
+            {:else}
+              ○
+            {/if}
+          </span>
+          <span class="label">{stepLabel}</span>
+          {#if isCurrent && progressPercent > 0}
+            <span class="step-pct">{progressPercent}%</span>
+          {/if}
+        </div>
+      {/each}
+    </div>
+
+    {#if showProgressBar}
+      <div class="progress-bar">
+        <div class="progress-fill" style="width: {progressPercent}%"></div>
+      </div>
+      <p class="progress-text">{progressPercent}%</p>
+    {/if}
+  </div>
+</div>
+
+<style>
+  .modal-overlay {
+    position: fixed;
+    inset: 0;
+    background: rgba(0, 0, 0, 0.7);
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    z-index: 1000;
+  }
+
+  .modal {
+    background: var(--bg-primary, #1e1e2e);
+    border: 1px solid var(--border, #353550);
+    border-radius: 12px;
+    padding: 32px 40px;
+    min-width: 360px;
+    max-width: 480px;
+    text-align: center;
+    box-shadow: 0 20px 60px rgba(0, 0, 0, 0.5);
+  }
+
+  h2 {
+    margin: 0 0 4px;
+    font-size: 18px;
+    font-weight: 600;
+    color: var(--text-primary, #cdd6f4);
+  }
+
+  .title {
+    margin: 0 0 24px;
+    font-size: 13px;
+    color: var(--text-secondary, #6c7086);
+    overflow: hidden;
+    text-overflow: ellipsis;
+    white-space: nowrap;
+  }
+
+  .steps {
+    display: flex;
+    flex-direction: column;
+    gap: 8px;
+    text-align: left;
+    margin-bottom: 20px;
+  }
+
+  .step {
+    display: flex;
+    align-items: center;
+    gap: 10px;
+    font-size: 13px;
+    color: var(--text-secondary, #6c7086);
+    transition: color 0.2s;
+  }
+
+  .step.done {
+    color: #a6e3a1;
+  }
+
+  .step.current {
+    color: var(--text-primary, #cdd6f4);
+    font-weight: 500;
+  }
+
+  .icon {
+    width: 18px;
+    text-align: center;
+    flex-shrink: 0;
+    font-size: 14px;
+  }
+
+  .step-pct {
+    margin-left: auto;
+    font-size: 12px;
+    color: var(--text-secondary, #6c7086);
+    font-weight: 400;
+  }
+
+  .progress-bar {
+    height: 6px;
+    background: var(--bg-tertiary, #2a2a3e);
+    border-radius: 3px;
+    overflow: hidden;
+    margin-bottom: 6px;
+  }
+
+  .progress-fill {
+    height: 100%;
+    background: #89b4fa;
+    border-radius: 3px;
+    transition: width 0.3s ease;
+  }
+
+  .progress-text {
+    margin: 0;
+    font-size: 12px;
+    color: var(--text-secondary, #6c7086);
+  }
+</style>
--- a/src/lib/components/StatusBar.svelte
+++ b/src/lib/components/StatusBar.svelte
@@ -1,32 +1,43 @@
 <script lang="ts">
-  import { session } from '$lib/stores/videoSession.svelte';
+  import { session, upgradePreview } from '$lib/stores/videoSession.svelte';

-  let progressPercent = $derived(Math.round(session.downloadProgress * 100));
-  let isDownloading = $derived(
+  let previewPercent = $derived(Math.round(session.previewProgress * 100));
+  let exportPercent = $derived(Math.round(session.exportProgress * 100));
+
+  let isPreviewDownloading = $derived(
    session.status === 'ready' &&
-      session.downloadStatus === 'downloading' &&
-      session.downloadProgress > 0 &&
-      session.downloadProgress < 1
-  );
-  let isDownloaded = $derived(
-    session.localFilePath !== null &&
-      (session.downloadStatus === 'complete' || session.downloadProgress >= 1)
+      session.previewStatus === 'downloading' &&
+      session.previewProgress > 0 &&
+      session.previewProgress < 1
  );
+
+  let isPreviewComplete = $derived(session.previewStatus === 'complete');
+  let isExportDownloading = $derived(session.exportStatus === 'downloading');
+  let isExportComplete = $derived(session.exportStatus === 'complete');
 </script>

 <div class="status-bar">
-  {#if isDownloading}
+  {#if isPreviewDownloading}
    <div class="progress-bar">
-      <div class="progress-fill" style="width: {progressPercent}%"></div>
+      <div class="progress-fill" style="width: {previewPercent}%"></div>
    </div>
-    <span class="status-text">Downloading: {progressPercent}%</span>
-  {:else if isDownloaded}
-    <span class="status-text success">✓ Downloaded: {session.title}</span>
+    <span class="status-text">Preview: {previewPercent}%</span>
+  {:else if isPreviewComplete && isExportDownloading}
+    <span class="status-text success">✓ Preview ready</span>
+    <div class="progress-bar">
+      <div class="progress-fill" style="width: {exportPercent}%"></div>
+    </div>
+    <span class="status-text">Best quality: {exportPercent}%</span>
+  {:else if isPreviewComplete && isExportComplete}
+    <span class="status-text success">✓ {session.title} — ready to export</span>
+    {#if session.showUpgradeToast}
+      <button class="upgrade-link" onclick={upgradePreview}>Reload Preview (HQ)</button>
+    {/if}
  {:else if session.status === 'resolving'}
    <span class="status-text">Resolving URL…</span>
-  {:else if session.status === 'ready' && session.downloadStatus === 'downloading'}
-    <span class="status-text">Starting download…</span>
-  {:else if session.downloadStatus === 'failed'}
+  {:else if session.status === 'ready' && session.previewStatus === 'idle'}
+    <span class="status-text">Preparing download…</span>
+  {:else if session.previewStatus === 'failed' || session.exportStatus === 'failed'}
    <span class="status-text">Download failed</span>
  {:else}
    <span class="status-text">Ready</span>
@@ -64,4 +75,20 @@
  .success {
    color: var(--success);
  }
+
+  .upgrade-link {
+    background: none;
+    border: 1px solid var(--accent, #89b4fa);
+    color: var(--accent, #89b4fa);
+    font-size: 11px;
+    padding: 2px 8px;
+    border-radius: 3px;
+    cursor: pointer;
+    white-space: nowrap;
+  }
+
+  .upgrade-link:hover {
+    background: var(--accent, #89b4fa);
+    color: var(--bg-primary, #1e1e2e);
+  }
 </style>
--- a/src/lib/components/Timeline.svelte
+++ b/src/lib/components/Timeline.svelte
@@ -8,15 +8,20 @@
  import { drawTimeline, type TimelineState } from '$lib/timeline/renderer';
  import {
    computeZoom,
+    panBy,
    handleClick as computeClickTime,
  } from '$lib/timeline/interactions';
  import { hitTestClip } from '$lib/timeline/clipRenderer';
+  import { drawWaveform, type WaveformData } from '$lib/timeline/waveformRenderer';
+  import { setThumbnailLoadCallback } from '$lib/timeline/thumbnailRenderer';

  type ClipDragTarget = { clipId: string; edge: 'start' | 'end' };

  let canvas = $state<HTMLCanvasElement | null>(null);
+  let minimapCanvas = $state<HTMLCanvasElement | null>(null);
  let containerEl = $state<HTMLDivElement | null>(null);
-  let animFrameId = $state(0);
+  let pendingDraw = 0;
+  let pendingMinimapDraw = 0;

  let timelineState = $state<TimelineState>({
    visibleStart: 0,
@@ -28,6 +33,139 @@

  let isDragging = $state(false);
  let dragTarget = $state<ClipDragTarget | null>(null);
+  let isMinimapDragging = $state(false);
+  let minimapDragStartX = $state(0);
+  let minimapDragStartVisibleStart = $state(0);
+
+  let isZoomed = $derived(timelineState.zoom > 1.01);
+
+  // Construct waveform data from pre-computed tiers — pure reactive, no IPC
+  let waveformData = $derived<WaveformData>({
+    tiers: session.waveformTiers,
+  });
+
+  // Register thumbnail load callback
+  $effect(() => {
+    setThumbnailLoadCallback(() => requestDraw());
+    return () => setThumbnailLoadCallback(null);
+  });
+
+  function requestDraw() {
+    if (!pendingDraw) {
+      pendingDraw = requestAnimationFrame(() => {
+        drawMainCanvas();
+        pendingDraw = 0;
+      });
+    }
+  }
+
+  function requestMinimapDraw() {
+    if (!pendingMinimapDraw) {
+      pendingMinimapDraw = requestAnimationFrame(() => {
+        drawMinimapCanvas();
+        pendingMinimapDraw = 0;
+      });
+    }
+  }
+
+  function drawMainCanvas() {
+    if (!canvas) return;
+    const ctx = canvas.getContext('2d');
+    if (!ctx) return;
+    ctx.save();
+    ctx.scale(window.devicePixelRatio, window.devicePixelRatio);
+    drawTimeline(
+      ctx,
+      timelineState,
+      session.currentTime,
+      session.duration,
+      clipStore.clips,
+      clipStore.selectedClipId,
+      clipStore.pendingInPoint,
+      waveformData,
+      session.thumbnailSpritesheets
+    );
+    ctx.restore();
+  }
+
+  function drawMinimapCanvas() {
+    if (!minimapCanvas || !isZoomed || session.duration <= 0) return;
+    const ctx = minimapCanvas.getContext('2d');
+    if (!ctx) return;
+    const w = minimapCanvas.width / window.devicePixelRatio;
+    const h = minimapCanvas.height / window.devicePixelRatio;
+
+    ctx.save();
+    ctx.scale(window.devicePixelRatio, window.devicePixelRatio);
+    ctx.clearRect(0, 0, w, h);
+
+    ctx.fillStyle = '#12121e';
+    ctx.fillRect(0, 0, w, h);
+
+    // Minimap always shows the overview tier at full duration
+    if (session.waveformTiers) {
+      const fullState: TimelineState = {
+        visibleStart: 0,
+        visibleEnd: session.duration,
+        zoom: 1,
+        width: w,
+        height: h,
+      };
+      const minimapWaveform: WaveformData = {
+        tiers: session.waveformTiers,
+      };
+      drawWaveform(ctx, fullState, minimapWaveform, session.duration, 0, h);
+    }
+
+    const vpLeft = (timelineState.visibleStart / session.duration) * w;
+    const vpRight = (timelineState.visibleEnd / session.duration) * w;
+
+    ctx.fillStyle = 'rgba(0, 0, 0, 0.5)';
+    ctx.fillRect(0, 0, vpLeft, h);
+    ctx.fillRect(vpRight, 0, w - vpRight, h);
+
+    ctx.strokeStyle = '#89b4fa';
+    ctx.lineWidth = 1.5;
+    ctx.strokeRect(vpLeft, 0, vpRight - vpLeft, h);
+
+    const phX = (session.currentTime / session.duration) * w;
+    ctx.strokeStyle = '#ffffff';
+    ctx.lineWidth = 1;
+    ctx.beginPath();
+    ctx.moveTo(phX, 0);
+    ctx.lineTo(phX, h);
+    ctx.stroke();
+
+    ctx.restore();
+  }
+
+  // Single unified redraw effect — coalesced by requestAnimationFrame
+  $effect(() => {
+    void session.currentTime;
+    void session.duration;
+    void session.waveformTiers;
+    void session.thumbnailSpritesheets;
+    void clipStore.clips;
+    void clipStore.selectedClipId;
+    void clipStore.pendingInPoint;
+    void timelineState.visibleStart;
+    void timelineState.visibleEnd;
+    void timelineState.width;
+    void timelineState.height;
+    void canvas;
+    requestDraw();
+  });
+
+  // Minimap redraws
+  $effect(() => {
+    void session.currentTime;
+    void session.waveformTiers;
+    void timelineState.visibleStart;
+    void timelineState.visibleEnd;
+    void isZoomed;
+    void minimapCanvas;
+    requestMinimapDraw();
+  });

  $effect(() => {
    if (session.duration > 0) {
@@ -56,31 +194,21 @@
  });

  $effect(() => {
-    if (!canvas) return;
-    const ctx = canvas.getContext('2d');
-    if (!ctx) return;
-
-    function draw() {
-      if (!ctx || !canvas) return;
-      ctx.save();
-      ctx.scale(window.devicePixelRatio, window.devicePixelRatio);
-      drawTimeline(
-        ctx,
-        timelineState,
-        session.currentTime,
-        session.duration,
-        clipStore.clips,
-        clipStore.selectedClipId,
-        clipStore.pendingInPoint,
-        session.waveformPeaks,
-        session.thumbnailSpritesheets
-      );
-      ctx.restore();
-      animFrameId = requestAnimationFrame(draw);
-    }
-
-    draw();
-    return () => cancelAnimationFrame(animFrameId);
+    if (!minimapCanvas || !containerEl) return;
+    const observer = new ResizeObserver((entries) => {
+      for (const entry of entries) {
+        if (minimapCanvas) {
+          const w = entry.contentRect.width;
+          const h = 28;
+          minimapCanvas.width = w * window.devicePixelRatio;
+          minimapCanvas.height = h * window.devicePixelRatio;
+          minimapCanvas.style.width = `${w}px`;
+          minimapCanvas.style.height = `${h}px`;
+        }
+      }
+    });
+    observer.observe(containerEl);
+    return () => observer.disconnect();
  });

  function getCanvasX(e: MouseEvent): number {
@@ -119,6 +247,7 @@
      return;
    }

+    selectClip(null);
    isDragging = true;
    const targetTime = computeClickTime(x, timelineState, session.duration);
    seekTo(targetTime);
@@ -156,6 +285,14 @@

  function handleWheel(e: WheelEvent) {
    e.preventDefault();
+
+    if (e.deltaX !== 0) {
+      const result = panBy(timelineState, e.deltaX, session.duration);
+      timelineState.visibleStart = result.visibleStart;
+      timelineState.visibleEnd = result.visibleEnd;
+      return;
+    }
+
    const x = getCanvasX(e);
    const anchorTime = computeClickTime(x, timelineState, session.duration);
    const factor = e.deltaY < 0 ? 1.15 : 0.87;
@@ -164,22 +301,121 @@
    timelineState.visibleEnd = result.visibleEnd;
    timelineState.zoom = result.zoom;
  }
+
+  function handleMinimapMouseDown(e: MouseEvent) {
+    if (!minimapCanvas || session.duration <= 0) return;
+    const rect = minimapCanvas.getBoundingClientRect();
+    const x = e.clientX - rect.left;
+    isMinimapDragging = true;
+    minimapDragStartX = x;
+    minimapDragStartVisibleStart = timelineState.visibleStart;
+  }
+
+  function handleMinimapMouseMove(e: MouseEvent) {
+    if (!isMinimapDragging || !minimapCanvas || session.duration <= 0) return;
+    const rect = minimapCanvas.getBoundingClientRect();
+    const x = e.clientX - rect.left;
+    const deltaX = x - minimapDragStartX;
+    const deltaTime = (deltaX / rect.width) * session.duration;
+    const range = timelineState.visibleEnd - timelineState.visibleStart;
+
+    let newStart = minimapDragStartVisibleStart + deltaTime;
+    let newEnd = newStart + range;
+
+    if (newStart < 0) {
+      newStart = 0;
+      newEnd = range;
+    }
+    if (newEnd > session.duration) {
+      newEnd = session.duration;
+      newStart = Math.max(0, newEnd - range);
+    }
+
+    timelineState.visibleStart = newStart;
+    timelineState.visibleEnd = newEnd;
+  }
+
+  function handleMinimapMouseUp() {
+    isMinimapDragging = false;
+  }
+
+  function handleMinimapClick(e: MouseEvent) {
+    if (!minimapCanvas || session.duration <= 0) return;
+    const rect = minimapCanvas.getBoundingClientRect();
+    const x = e.clientX - rect.left;
+    const clickTime = (x / rect.width) * session.duration;
+    const range = timelineState.visibleEnd - timelineState.visibleStart;
+
+    let newStart = clickTime - range / 2;
+    let newEnd = newStart + range;
+    if (newStart < 0) {
+      newStart = 0;
+      newEnd = range;
+    }
+    if (newEnd > session.duration) {
+      newEnd = session.duration;
+      newStart = Math.max(0, newEnd - range);
+    }
+    timelineState.visibleStart = newStart;
+    timelineState.visibleEnd = newEnd;
+  }
 </script>

-<div class="timeline-container" bind:this={containerEl}>
-  <canvas
-    bind:this={canvas}
-    onmousedown={handleMouseDown}
-    onmousemove={handleMouseMove}
-    onmouseup={handleMouseUp}
-    onmouseleave={handleMouseUp}
-    onwheel={handleWheel}
-  ></canvas>
+<div class="timeline-wrapper">
+  {#if isZoomed}
+    <div class="minimap">
+      <canvas
+        bind:this={minimapCanvas}
+        onmousedown={handleMinimapMouseDown}
+        onclick={handleMinimapClick}
+      ></canvas>
+    </div>
+  {/if}
+  <div class="timeline-container" bind:this={containerEl}>
+    <canvas
+      bind:this={canvas}
+      onmousedown={handleMouseDown}
+      onmousemove={handleMouseMove}
+      onmouseup={handleMouseUp}
+      onmouseleave={handleMouseUp}
+      onwheel={handleWheel}
+    ></canvas>
+  </div>
 </div>

+<svelte:window
+  onmousemove={handleMinimapMouseMove}
+  onmouseup={handleMinimapMouseUp}
+/>
+
 <style>
+  .timeline-wrapper {
+    display: flex;
+    flex-direction: column;
+    height: 100%;
+  }
+
+  .minimap {
+    height: 28px;
+    background: #12121e;
+    border-bottom: 1px solid var(--border, #353550);
+    cursor: grab;
+    flex-shrink: 0;
+  }
+
+  .minimap:active {
+    cursor: grabbing;
+  }
+
+  .minimap canvas {
+    display: block;
+    width: 100%;
+    height: 100%;
+  }
+
  .timeline-container {
-    height: 160px;
+    flex: 1;
+    min-height: 80px;
    background: var(--timeline-bg);
    position: relative;
    cursor: crosshair;
--- a/src/lib/components/TransportControls.svelte
+++ b/src/lib/components/TransportControls.svelte
@@ -8,11 +8,35 @@
    seekBy,
    stepFrame,
    togglePlayPause,
+    setVolume,
+    setMuted,
+    getVolume,
+    getMuted,
    type TransportKeyAction,
  } from '$lib/transport/playback';

  let hasKeyframes = $derived(session.keyframePositions.length > 0);

+  let volume = $state(1);
+  let isMuted = $state(false);
+
+  function toggleMute() {
+    isMuted = !isMuted;
+    setMuted(isMuted);
+  }
+
+  function handleVolumeChange(e: Event) {
+    const val = parseFloat((e.target as HTMLInputElement).value);
+    volume = val;
+    if (val > 0 && isMuted) {
+      isMuted = false;
+    }
+    setVolume(val);
+    if (val > 0) {
+      setMuted(false);
+    }
+  }
+
  export function handleKeyAction(action: TransportKeyAction) {
    runTransportAction(action, markInPoint, markOutPoint);
  }
@@ -53,6 +77,32 @@
    <span class="total">{formatTime(session.duration)}</span>
  </div>

+  <div class="volume-controls">
+    <button
+      class="vol-btn"
+      onclick={toggleMute}
+      title={isMuted ? 'Unmute' : 'Mute'}
+      type="button"
+    >
+      {#if isMuted || volume === 0}
+        🔇
+      {:else if volume < 0.5}
+        🔉
+      {:else}
+        🔊
+      {/if}
+    </button>
+    <input
+      type="range"
+      class="vol-slider"
+      min="0"
+      max="1"
+      step="0.05"
+      value={isMuted ? 0 : volume}
+      oninput={handleVolumeChange}
+    />
+  </div>
+
  <div class="mark-buttons">
    <button
      class="mark-btn"
@@ -114,6 +164,34 @@
    color: var(--text-secondary);
  }

+  .volume-controls {
+    display: flex;
+    align-items: center;
+    gap: 4px;
+  }
+
+  .vol-btn {
+    background: var(--bg-tertiary);
+    border: 1px solid var(--border);
+    border-radius: 4px;
+    padding: 3px 6px;
+    font-size: 14px;
+    cursor: pointer;
+    line-height: 1;
+    color: var(--text-secondary);
+  }
+
+  .vol-btn:hover {
+    color: var(--text-primary);
+  }
+
+  .vol-slider {
+    width: 80px;
+    height: 4px;
+    accent-color: #89b4fa;
+    cursor: pointer;
+  }
+
  .mark-buttons {
    margin-left: auto;
    display: flex;
--- a/src/lib/components/UrlInput.svelte
+++ b/src/lib/components/UrlInput.svelte
@@ -9,11 +9,17 @@
  } from '$lib/stores/videoSession.svelte';

  let inputValue = $state('');
+  let inputEl = $state<HTMLInputElement | null>(null);
+
+  function blurInput() {
+    inputEl?.blur();
+  }

  async function handleSubmit() {
    const trimmed = inputValue.trim();
    if (!trimmed) return;

+    blurInput();
    setResolving();
    try {
      const meta = await resolveUrl(trimmed);
@@ -43,6 +49,7 @@
 <div class="url-input-wrapper">
  <div class="url-input">
    <input
+      bind:this={inputEl}
      type="text"
      placeholder="Paste a video URL and press Enter…"
      bind:value={inputValue}
--- a/src/lib/stores/clips.svelte.ts
+++ b/src/lib/stores/clips.svelte.ts
@@ -8,6 +8,8 @@ export interface Clip {
  color: string;
 }

+const EDIT_TOLERANCE = 0.5; // seconds — how close the playhead must be to a clip edge to count as "inside"
+
 export const clipStore = $state({
  clips: [] as Clip[],
  selectedClipId: null as string | null,
@@ -27,9 +29,20 @@ export function getPendingInPoint(): number | null {
  return clipStore.pendingInPoint;
 }

+function isTimeInsideClip(time: number, clipId: string): boolean {
+  const clip = clipStore.clips.find((c) => c.id === clipId);
+  if (!clip) return false;
+  return time >= clip.startTime - EDIT_TOLERANCE && time <= clip.endTime + EDIT_TOLERANCE;
+}
+
 export function selectClip(id: string | null) {
  clipStore.selectedClipId = id;
-  clipStore.pendingInPoint = null;
+  // Only clear pendingInPoint when selecting a specific clip.
+  // When deselecting (id=null), preserve it so clicking the timeline
+  // to seek after pressing I doesn't lose the pending in-point.
+  if (id !== null) {
+    clipStore.pendingInPoint = null;
+  }
 }

 export function addClip(startTime: number, endTime: number): Clip {
@@ -71,20 +84,32 @@ export function updateClip(
 }

 export function markInPoint(time: number) {
-  if (clipStore.selectedClipId) {
+  if (
+    clipStore.selectedClipId &&
+    isTimeInsideClip(time, clipStore.selectedClipId)
+  ) {
+    // Playhead is inside the selected clip — edit its in-point
    updateClip(clipStore.selectedClipId, { startTime: time });
  } else {
+    // Playhead is outside — deselect and begin a new clip
+    clipStore.selectedClipId = null;
    clipStore.pendingInPoint = time;
  }
 }

 export function markOutPoint(time: number) {
-  if (clipStore.selectedClipId) {
+  if (
+    clipStore.selectedClipId &&
+    isTimeInsideClip(time, clipStore.selectedClipId)
+  ) {
+    // Playhead is inside the selected clip — edit its out-point
    updateClip(clipStore.selectedClipId, { endTime: time });
  } else if (clipStore.pendingInPoint !== null) {
+    // We have a pending in-point — create a new clip
    addClip(clipStore.pendingInPoint, time);
    clipStore.pendingInPoint = null;
  }
+  // Otherwise (no selection, no pending in-point) — no-op
 }

 export function clearAll() {
--- a/src/lib/stores/videoSession.svelte.ts
+++ b/src/lib/stores/videoSession.svelte.ts
@@ -1,17 +1,33 @@
 import type { VideoMetadata } from '$lib/bindings/video';
-import { startDownload } from '$lib/bindings/video';
-import type { ThumbnailSpritesheet } from '$lib/bindings/mediaAnalysis';
+import { checkCachedDownload, downloadSubtitles, startDownload } from '$lib/bindings/video';
+import type { ThumbnailSpritesheet, WaveformTiers } from '$lib/bindings/mediaAnalysis';
 import {
+  checkEmbeddedSubtitles,
  cleanupThumbnails,
  extractKeyframes,
  extractThumbnails,
-  extractWaveform,
+  extractWaveformTiers,
 } from '$lib/bindings/mediaAnalysis';
 import { clearThumbnailCache } from '$lib/timeline/thumbnailRenderer';
 import { clearAll as clearAllClips } from '$lib/stores/clips.svelte';

 export type SessionStatus = 'idle' | 'resolving' | 'ready' | 'error';
 export type DownloadStatus = 'idle' | 'downloading' | 'complete' | 'failed';
+export type ProcessingStep =
+  | 'idle'
+  | 'downloading'
+  | 'waveform'
+  | 'keyframes'
+  | 'thumbnails'
+  | 'captions'
+  | 'done';
+
+// H.264+AAC ≤360p for fast preview/scrubbing in WKWebView
+const PREVIEW_FORMAT =
+  'bv*[vcodec^=avc1][height<=360]+ba[acodec^=mp4a]/b[ext=mp4][height<=360]/worst[ext=mp4]/worst';
+// Best available H.264+AAC in MP4 for export — WKWebView can't play AV1/VP9/WebM
+const EXPORT_FORMAT =
+  'bv*[vcodec^=avc1]+ba[acodec^=mp4a]/b[ext=mp4]/best[ext=mp4]';

 export const session = $state({
  status: 'idle' as SessionStatus,
@@ -24,12 +40,35 @@ export const session = $state({
  streamUrl: '',
  currentTime: 0,
  isPlaying: false,
-  localFilePath: null as string | null,
-  downloadProgress: 0,
-  downloadStatus: 'idle' as DownloadStatus,
+
+  // Preview (low-res for playback/scrubbing/waveform/thumbnails)
+  previewFilePath: null as string | null,
+  previewProgress: 0,
+  previewStatus: 'idle' as DownloadStatus,
+
+  // Export (best quality for clip extraction)
+  exportFilePath: null as string | null,
+  exportProgress: 0,
+  exportStatus: 'idle' as DownloadStatus,
+
  keyframePositions: [] as number[],
-  waveformPeaks: [] as number[],
+  waveformTiers: null as WaveformTiers | null,
  thumbnailSpritesheets: [] as ThumbnailSpritesheet[],
+
+  // Captions
+  hasCaptions: false,
+  captionsAreAuto: false,
+  captionFilePath: null as string | null,
+
+  // The path used for the <video> element (may be preview or export quality)
+  activeVideoPath: null as string | null,
+
+  // Preview upgrade toast
+  showUpgradeToast: false,
+
+  // Processing modal state
+  processingStep: 'idle' as ProcessingStep,
+  processingProgress: 0,
 });

 export function setMetadata(meta: VideoMetadata) {
@@ -40,15 +79,25 @@ export function setMetadata(meta: VideoMetadata) {
  session.fps = meta.fps;
  session.thumbnailUrl = meta.thumbnailUrl;
  session.streamUrl = meta.streamUrl;
+  session.hasCaptions = meta.hasCaptions;
+  session.captionsAreAuto = meta.captionsAreAuto;
  session.status = 'ready';
  session.error = null;

-  session.localFilePath = null;
-  session.downloadProgress = 0;
-  session.downloadStatus = 'idle';
+  session.captionFilePath = null;
+  session.previewFilePath = null;
+  session.previewProgress = 0;
+  session.previewStatus = 'idle';
+  session.exportFilePath = null;
+  session.exportProgress = 0;
+  session.exportStatus = 'idle';
  session.keyframePositions = [];
-  session.waveformPeaks = [];
+  session.waveformTiers = null;
  session.thumbnailSpritesheets = [];
+  session.activeVideoPath = null;
+  session.showUpgradeToast = false;
+  session.processingStep = 'idle';
+  session.processingProgress = 0;
 }

 function clearMediaFields() {
@@ -60,12 +109,22 @@ function clearMediaFields() {
  session.streamUrl = '';
  session.currentTime = 0;
  session.isPlaying = false;
-  session.localFilePath = null;
-  session.downloadProgress = 0;
-  session.downloadStatus = 'idle';
+  session.previewFilePath = null;
+  session.previewProgress = 0;
+  session.previewStatus = 'idle';
+  session.exportFilePath = null;
+  session.exportProgress = 0;
+  session.exportStatus = 'idle';
  session.keyframePositions = [];
-  session.waveformPeaks = [];
+  session.waveformTiers = null;
  session.thumbnailSpritesheets = [];
+  session.hasCaptions = false;
+  session.captionsAreAuto = false;
+  session.captionFilePath = null;
+  session.activeVideoPath = null;
+  session.showUpgradeToast = false;
+  session.processingStep = 'idle';
+  session.processingProgress = 0;
 }

 export function setError(msg: string) {
@@ -87,45 +146,112 @@ export function reset() {
  session.error = null;
 }

-async function triggerPostDownloadProcessing(filePath: string) {
-  const duration = session.duration;
-  const [keyframes, waveform, thumbnails] = await Promise.allSettled([
-    extractKeyframes(filePath),
-    extractWaveform(filePath, 8000),
-    extractThumbnails(filePath, duration),
-  ]);
-
-  if (keyframes.status === 'fulfilled') {
-    session.keyframePositions = keyframes.value;
-  } else {
-    console.error('Keyframe extraction failed:', keyframes.reason);
-  }
-
-  if (waveform.status === 'fulfilled') {
-    session.waveformPeaks = waveform.value;
-  } else {
-    console.error('Waveform extraction failed:', waveform.reason);
-  }
-
-  if (thumbnails.status === 'fulfilled') {
-    session.thumbnailSpritesheets = thumbnails.value;
-  } else {
-    console.error('Thumbnail extraction failed:', thumbnails.reason);
+/** Switch the preview video to the full-quality export version. */
+export function upgradePreview() {
+  if (session.exportFilePath) {
+    console.log('[upgradePreview] switching from', session.activeVideoPath, 'to', session.exportFilePath);
+    session.activeVideoPath = session.exportFilePath;
+    session.showUpgradeToast = false;
  }
 }

+export function dismissUpgradeToast() {
+  session.showUpgradeToast = false;
+}
+
+async function loadCaptions(filePath: string) {
+  session.processingStep = 'captions';
+
+  // Priority 1: Check for embedded subtitle streams in the file
+  try {
+    const embeddedPath = await checkEmbeddedSubtitles(filePath);
+    if (embeddedPath) {
+      session.captionFilePath = embeddedPath;
+      return;
+    }
+  } catch (err) {
+    console.error('Embedded subtitle check failed:', err);
+  }
+
+  // Priority 2: Download external subtitles via yt-dlp (manual > auto-generated)
+  if (session.hasCaptions && session.url) {
+    try {
+      const path = await downloadSubtitles(session.url, session.captionsAreAuto);
+      session.captionFilePath = path;
+    } catch (err) {
+      console.error('Subtitle download failed:', err);
+    }
+  }
+}
+
+async function triggerPostDownloadProcessing(filePath: string) {
+  const duration = session.duration;
+
+  // Run processing SEQUENTIALLY to avoid overloading the CPU with
+  // concurrent ffmpeg subprocesses. Each one decodes the full file.
+  // Order: waveform first (most useful for editing), then keyframes, then thumbnails.
+
+  session.processingStep = 'waveform';
+  session.processingProgress = 0;
+  try {
+    const tiers = await extractWaveformTiers(filePath, duration, (pct) => {
+      session.processingProgress = pct;
+    });
+    session.waveformTiers = tiers;
+  } catch (err) {
+    console.error('Waveform extraction failed:', err);
+  }
+
+  session.processingStep = 'keyframes';
+  session.processingProgress = 0;
+  try {
+    const kf = await extractKeyframes(filePath);
+    session.keyframePositions = kf;
+  } catch (err) {
+    console.error('Keyframe extraction failed:', err);
+  }
+
+  session.processingStep = 'thumbnails';
+  session.processingProgress = 0;
+  try {
+    const sheets = await extractThumbnails(filePath, duration);
+    session.thumbnailSpritesheets = sheets;
+  } catch (err) {
+    console.error('Thumbnail extraction failed:', err);
+  }
+
+  // Captions can run after analysis since they use yt-dlp, not ffmpeg
+  await loadCaptions(filePath);
+
+  session.processingStep = 'done';
+
+  // If export download already completed while we were processing, show upgrade toast
+  if (session.exportStatus === 'complete' && session.exportFilePath) {
+    session.showUpgradeToast = true;
+  }
+}
+
+async function runDownload(
+  url: string,
+  formatSpec: string,
+  outputDir: string,
+  onProgress: (pct: number) => void,
+  onFilePath: (path: string) => void,
+  onFinished: (success: boolean, path: string) => void,
+  onError: (message: string) => void,
+): Promise<void> {
+  await startDownload(url, formatSpec, outputDir, onProgress, onFilePath, onFinished, onError);
+}
+
 export async function beginDownload() {
-  if (!session.url) return;
+  if (!session.url || !session.title) return;

  const oldThumbnailDirs = [
    ...new Set(session.thumbnailSpritesheets.map((sheet) => sheet.filePath)),
  ];
  clearThumbnailCache();
-  session.downloadStatus = 'downloading';
-  session.downloadProgress = 0;
-  session.localFilePath = null;
  session.keyframePositions = [];
-  session.waveformPeaks = [];
+  session.waveformTiers = null;
  session.thumbnailSpritesheets = [];

  if (oldThumbnailDirs.length > 0) {
@@ -134,32 +260,90 @@ export async function beginDownload() {
    });
  }

-  try {
-    await startDownload(
+  session.processingStep = 'downloading';
+
+  // --- Preview download (low-res, fast) ---
+  const previewCached = await checkCachedDownload(session.title, 'preview').catch(() => null);
+  if (previewCached) {
+    session.previewFilePath = previewCached;
+    session.activeVideoPath = previewCached;
+    session.previewProgress = 1.0;
+    session.previewStatus = 'complete';
+    triggerPostDownloadProcessing(previewCached);
+  } else {
+    session.previewStatus = 'downloading';
+    session.previewProgress = 0;
+    session.previewFilePath = null;
+
+    try {
+      await runDownload(
+        session.url,
+        PREVIEW_FORMAT,
+        'preview',
+        (pct) => { session.previewProgress = pct; },
+        (path) => { session.previewFilePath = path; },
+        (success, path) => {
+          if (success) {
+            session.previewProgress = 1.0;
+            session.previewFilePath = path;
+            session.activeVideoPath = path;
+            session.previewStatus = 'complete';
+            triggerPostDownloadProcessing(path);
+          } else {
+            session.previewStatus = 'failed';
+          }
+        },
+        (message) => {
+          session.previewStatus = 'failed';
+          console.error('Preview download error:', message);
+        }
+      );
+    } catch (e) {
+      session.previewStatus = 'failed';
+      console.error('Preview download failed:', e);
+    }
+  }
+
+  // --- Export download (best quality, background) ---
+  const exportCached = await checkCachedDownload(session.title, 'export').catch(() => null);
+  if (exportCached) {
+    session.exportFilePath = exportCached;
+    session.exportProgress = 1.0;
+    session.exportStatus = 'complete';
+    if ((session.processingStep as ProcessingStep) === 'done') {
+      session.showUpgradeToast = true;
+    }
+  } else {
+    session.exportStatus = 'downloading';
+    session.exportProgress = 0;
+    session.exportFilePath = null;
+
+    // Fire-and-forget — runs in background
+    runDownload(
      session.url,
-      (percent) => {
-        session.downloadProgress = percent;
-      },
-      (path) => {
-        session.localFilePath = path;
-      },
+      EXPORT_FORMAT,
+      'export',
+      (pct) => { session.exportProgress = pct; },
+      (path) => { session.exportFilePath = path; },
      (success, path) => {
        if (success) {
-          session.downloadProgress = 1.0;
-          session.localFilePath = path;
-          session.downloadStatus = 'complete';
-          void triggerPostDownloadProcessing(path);
+          session.exportProgress = 1.0;
+          session.exportFilePath = path;
+          session.exportStatus = 'complete';
+          if ((session.processingStep as ProcessingStep) === 'done') {
+            session.showUpgradeToast = true;
+          }
        } else {
-          session.downloadStatus = 'failed';
+          session.exportStatus = 'failed';
        }
      },
      (message) => {
-        session.downloadStatus = 'failed';
-        console.error('Download error:', message);
+        session.exportStatus = 'failed';
+        console.error('Export download error:', message);
      }
-    );
-  } catch (e) {
-    session.downloadStatus = 'failed';
-    console.error('Download failed:', e);
+    ).catch((e) => {
+      session.exportStatus = 'failed';
+      console.error('Export download failed:', e);
+    });
  }
 }
--- a/src/lib/timeline/interactions.ts
+++ b/src/lib/timeline/interactions.ts
@@ -45,6 +45,28 @@ export function computeZoom(
  return { visibleStart: newStart, visibleEnd: newEnd, zoom: newZoom };
 }

+export function panBy(
+  state: TimelineState,
+  deltaPixels: number,
+  duration: number
+): { visibleStart: number; visibleEnd: number } {
+  const range = state.visibleEnd - state.visibleStart;
+  const deltaTime = (deltaPixels / state.width) * range;
+  let newStart = state.visibleStart + deltaTime;
+  let newEnd = newStart + range;
+
+  if (newStart < 0) {
+    newStart = 0;
+    newEnd = range;
+  }
+  if (newEnd > duration) {
+    newEnd = duration;
+    newStart = Math.max(0, newEnd - range);
+  }
+
+  return { visibleStart: newStart, visibleEnd: newEnd };
+}
+
 export function handleClick(
  x: number,
  state: TimelineState,
--- a/src/lib/timeline/renderer.ts
+++ b/src/lib/timeline/renderer.ts
@@ -1,6 +1,6 @@
 import { drawClips } from './clipRenderer';
 import type { Clip } from '$lib/stores/clips.svelte';
-import { drawWaveform } from './waveformRenderer';
+import { drawWaveform, type WaveformData } from './waveformRenderer';
 import { drawThumbnails } from './thumbnailRenderer';
 import type { ThumbnailSpritesheet } from '$lib/bindings/mediaAnalysis';

@@ -36,7 +36,7 @@ export function drawTimeline(
  clips: Clip[] = [],
  selectedClipId: string | null = null,
  pendingInPoint: number | null = null,
-  waveformPeaks: number[] = [],
+  waveform: WaveformData = { tiers: null },
  thumbnailSpritesheets: ThumbnailSpritesheet[] = []
 ): void {
  const { width, height } = state;
@@ -53,8 +53,8 @@ export function drawTimeline(
    drawPlaceholderLane(ctx, state, 0, THUMB_LANE_HEIGHT, 'Thumbnails');
  }

-  if (waveformPeaks.length > 0) {
-    drawWaveform(ctx, state, waveformPeaks, duration, THUMB_LANE_HEIGHT, WAVEFORM_LANE_HEIGHT);
+  if (waveform.tiers) {
+    drawWaveform(ctx, state, waveform, duration, THUMB_LANE_HEIGHT, WAVEFORM_LANE_HEIGHT);
  } else {
    drawPlaceholderLane(ctx, state, THUMB_LANE_HEIGHT, WAVEFORM_LANE_HEIGHT, 'Waveform');
  }
--- a/src/lib/timeline/thumbnailRenderer.ts
+++ b/src/lib/timeline/thumbnailRenderer.ts
@@ -3,9 +3,17 @@ import { convertFileSrc } from '@tauri-apps/api/core';
 import { timeToX, type TimelineState } from './renderer';

 const imageCache = new Map<string, HTMLImageElement>();
+const pendingLoads = new Set<string>();
+let onLoadCallback: (() => void) | null = null;

 export function clearThumbnailCache(): void {
  imageCache.clear();
+  pendingLoads.clear();
+}
+
+/** Register a callback to be invoked when any thumbnail finishes loading */
+export function setThumbnailLoadCallback(cb: (() => void) | null): void {
+  onLoadCallback = cb;
 }

 const TARGET_SPACING_PX = 100;
@@ -16,14 +24,21 @@ function getImagePath(dir: string, frameIndex: number): string {
 }

 function loadImage(path: string): void {
-  if (imageCache.has(path)) {
+  if (imageCache.has(path) || pendingLoads.has(path)) {
    return;
  }

+  pendingLoads.add(path);
  const img = new Image();
  img.src = convertFileSrc(path);
-  img.onload = () => imageCache.set(path, img);
-  imageCache.set(path, img);
+  img.onload = () => {
+    imageCache.set(path, img);
+    pendingLoads.delete(path);
+    onLoadCallback?.();
+  };
+  img.onerror = () => {
+    pendingLoads.delete(path);
+  };
 }

 function findSheetForFrame(
--- a/src/lib/timeline/waveformRenderer.ts
+++ b/src/lib/timeline/waveformRenderer.ts
@@ -1,17 +1,64 @@
+import type { WaveformTiers } from '$lib/bindings/mediaAnalysis';
 import type { TimelineState } from './renderer';

+export interface WaveformData {
+  tiers: WaveformTiers | null;
+}
+
+/**
+ * Pick the best tier for the current viewport.
+ * Returns the tier array that gives at least 1 peak per pixel,
+ * preferring the lowest-resolution tier that meets that threshold.
+ */
+function pickTier(
+  tiers: WaveformTiers,
+  visibleStart: number,
+  visibleEnd: number,
+  duration: number,
+  widthPx: number
+): number[] {
+  const visibleRange = visibleEnd - visibleStart;
+  const visibleFraction = visibleRange / duration;
+
+  const candidates: [number[], number][] = [
+    [tiers.tier0, (tiers.tier0.length * visibleFraction) / widthPx],
+    [tiers.tier1, (tiers.tier1.length * visibleFraction) / widthPx],
+    [tiers.tier2, (tiers.tier2.length * visibleFraction) / widthPx],
+  ];
+
+  for (const [tier, peaksPerPx] of candidates) {
+    if (peaksPerPx >= 1) return tier;
+  }
+
+  return tiers.tier2;
+}
+
 export function drawWaveform(
  ctx: CanvasRenderingContext2D,
  state: TimelineState,
-  peaks: number[],
+  waveform: WaveformData,
  duration: number,
  y: number,
  height: number
 ): void {
-  if (peaks.length === 0 || duration <= 0) return;
+  if (duration <= 0 || !waveform.tiers) return;

  const { width, visibleStart, visibleEnd } = state;
  const visibleRange = visibleEnd - visibleStart;
+  const peaks = pickTier(waveform.tiers, visibleStart, visibleEnd, duration, width);
+  const peakCount = peaks.length;
+
+  // Find local maximum across the visible region for dynamic scaling.
+  // This makes the waveform fill the available height when zoomed in,
+  // rather than staying relative to the global max.
+  const visStartIdx = Math.max(0, Math.floor((visibleStart / duration) * peakCount));
+  const visEndIdx = Math.min(peakCount - 1, Math.ceil((visibleEnd / duration) * peakCount));
+  let localMax = 0;
+  for (let i = visStartIdx; i <= visEndIdx; i++) {
+    localMax = Math.max(localMax, peaks[i]);
+  }
+  // Avoid division by zero; use 1.0 if all peaks are silent
+  const scale = localMax > 0 ? 1 / localMax : 1;

  ctx.fillStyle = '#89b4fa44';
  ctx.strokeStyle = '#89b4fa88';
@@ -21,19 +68,18 @@ export function drawWaveform(
  ctx.moveTo(0, y + height);

  for (let px = 0; px < width; px++) {
-    const startSample = Math.floor(
-      ((visibleStart + ((px - 0.5) / width) * visibleRange) / duration) * peaks.length
-    );
-    const endSample = Math.floor(
-      ((visibleStart + ((px + 0.5) / width) * visibleRange) / duration) * peaks.length
-    );
+    const timeStart = visibleStart + ((px - 0.5) / width) * visibleRange;
+    const timeEnd = visibleStart + ((px + 0.5) / width) * visibleRange;
+
+    const s0 = Math.floor((timeStart / duration) * peakCount);
+    const s1 = Math.floor((timeEnd / duration) * peakCount);

    let maxPeak = 0;
-    for (let i = Math.max(0, startSample); i <= Math.min(endSample, peaks.length - 1); i++) {
+    for (let i = Math.max(0, s0); i <= Math.min(s1, peakCount - 1); i++) {
      maxPeak = Math.max(maxPeak, peaks[i]);
    }

-    const barHeight = maxPeak * height;
+    const barHeight = maxPeak * scale * height;
    ctx.lineTo(px, y + height - barHeight);
  }

--- a/src/lib/transport/playback.ts
+++ b/src/lib/transport/playback.ts
@@ -1,9 +1,19 @@
 import { session } from '$lib/stores/videoSession.svelte';

+let _videoEl: HTMLVideoElement | null = null;
+
+export function setVideoElement(el: HTMLVideoElement | null) {
+  _videoEl = el;
+}
+
+function getVideo(): HTMLVideoElement | null {
+  return _videoEl;
+}
+
 export function seekTo(time: number) {
  const clamped = Math.max(0, Math.min(time, session.duration));
  session.currentTime = clamped;
-  const videoEl = document.querySelector('video');
+  const videoEl = getVideo();
  if (videoEl) {
    videoEl.currentTime = clamped;
  }
@@ -14,7 +24,7 @@ export function seekBy(seconds: number) {
 }

 export function togglePlayPause() {
-  const videoEl = document.querySelector('video');
+  const videoEl = getVideo();
  if (!videoEl) return;
  if (videoEl.paused) {
    void videoEl.play();
@@ -24,7 +34,7 @@ export function togglePlayPause() {
 }

 export function stepFrame(direction: 1 | -1) {
-  const videoEl = document.querySelector('video');
+  const videoEl = getVideo();
  if (videoEl && !videoEl.paused) {
    videoEl.pause();
  }
@@ -44,15 +54,38 @@ export function jumpKeyframe(direction: 1 | -1) {
  }
 }

+export function setVolume(v: number) {
+  const videoEl = getVideo();
+  if (videoEl) {
+    videoEl.volume = v;
+    videoEl.muted = false;
+  }
+}
+
+export function setMuted(m: boolean) {
+  const videoEl = getVideo();
+  if (videoEl) {
+    videoEl.muted = m;
+  }
+}
+
+export function getVolume(): number {
+  return getVideo()?.volume ?? 1;
+}
+
+export function getMuted(): boolean {
+  return getVideo()?.muted ?? false;
+}
+
 export function resetShuttleRate() {
-  const videoEl = document.querySelector('video');
+  const videoEl = getVideo();
  if (videoEl) {
    videoEl.playbackRate = 1;
  }
 }

 export function adjustShuttle(dir: 1 | -1, shuttleRate: number): number {
-  const videoEl = document.querySelector('video');
+  const videoEl = getVideo();
  if (!videoEl) return shuttleRate;

  const nextRate = Math.max(0.25, Math.min(4, shuttleRate + dir * 0.5));
--- a/src/lib/utils/vttParser.ts
+++ b/src/lib/utils/vttParser.ts
@@ -0,0 +1,142 @@
+export interface WordSegment {
+  text: string;
+  startTime: number;
+}
+
+export interface VttCue {
+  startTime: number;
+  endTime: number;
+  text: string;
+  words?: WordSegment[];
+}
+
+/**
+ * Parse a WebVTT string into an array of cues.
+ * Handles both standard VTT and common variations.
+ * Extracts word-level timing data from YouTube-style <c> tags when present.
+ */
+export function parseVtt(vttContent: string): VttCue[] {
+  const cues: VttCue[] = [];
+  const blocks = vttContent.replace(/\r\n/g, '\n').split(/\n\n+/);
+
+  for (const block of blocks) {
+    const lines = block.trim().split('\n');
+    let timestampLineIdx = -1;
+    for (let i = 0; i < lines.length; i++) {
+      if (lines[i].includes('-->')) {
+        timestampLineIdx = i;
+        break;
+      }
+    }
+    if (timestampLineIdx === -1) continue;
+
+    const timestampLine = lines[timestampLineIdx];
+    const match = timestampLine.match(
+      /(\d{1,2}:?\d{2}:\d{2}[.,]\d{3})\s*-->\s*(\d{1,2}:?\d{2}:\d{2}[.,]\d{3})/
+    );
+    if (!match) continue;
+
+    const startTime = parseTimestamp(match[1]);
+    const endTime = parseTimestamp(match[2]);
+
+    const rawText = lines
+      .slice(timestampLineIdx + 1)
+      .join('\n')
+      .trim();
+
+    const words = parseWordTimings(rawText, startTime);
+    const text = rawText.replace(/<[^>]+>/g, '').trim();
+
+    if (text && startTime < endTime) {
+      cues.push({ startTime, endTime, text, words: words.length > 0 ? words : undefined });
+    }
+  }
+
+  return cues;
+}
+
+/**
+ * Parse word-level timing data from YouTube-style VTT cue text.
+ *
+ * YouTube format: `the<00:00:00.599><c> gym</c><00:00:00.840><c> I</c>`
+ *
+ * The first word(s) before any timestamp tag start at `cueStartTime`.
+ * Each `<HH:MM:SS.mmm>` sets the start time for the text in the following `<c>...</c>`.
+ */
+function parseWordTimings(rawText: string, cueStartTime: number): WordSegment[] {
+  // Only parse if the text contains the YouTube-style <c> word timing pattern
+  if (!rawText.includes('<c>')) return [];
+
+  const segments: WordSegment[] = [];
+  // Pattern to match: optional leading text, then repeated <timestamp><c> word</c> groups
+  // We process the raw text character by character using regex matches
+
+  // Match all timestamp + <c>word</c> pairs, plus any leading text
+  const timestampCPattern = /<(\d{1,2}:?\d{2}:\d{2}[.,]\d{3})><c>(.*?)<\/c>/g;
+
+  // Get any leading text before the first timestamp
+  const firstTimestampMatch = rawText.match(/<\d{1,2}:?\d{2}:\d{2}[.,]\d{3}>/);
+  if (firstTimestampMatch && firstTimestampMatch.index !== undefined && firstTimestampMatch.index > 0) {
+    const leadingText = rawText.substring(0, firstTimestampMatch.index).replace(/<[^>]+>/g, '').trim();
+    if (leadingText) {
+      segments.push({ text: leadingText, startTime: cueStartTime });
+    }
+  }
+
+  let m: RegExpExecArray | null;
+  while ((m = timestampCPattern.exec(rawText)) !== null) {
+    const wordTime = parseTimestamp(m[1]);
+    const wordText = m[2].replace(/<[^>]+>/g, '').trim();
+    if (wordText) {
+      segments.push({ text: wordText, startTime: wordTime });
+    }
+  }
+
+  return segments;
+}
+
+/**
+ * Parse a VTT/SRT timestamp like "00:01:23.456" or "1:23.456" into seconds.
+ */
+function parseTimestamp(ts: string): number {
+  const normalized = ts.replace(',', '.');
+  const parts = normalized.split(':');
+  if (parts.length === 3) {
+    return (
+      parseInt(parts[0], 10) * 3600 +
+      parseInt(parts[1], 10) * 60 +
+      parseFloat(parts[2])
+    );
+  } else if (parts.length === 2) {
+    return parseInt(parts[0], 10) * 60 + parseFloat(parts[1]);
+  }
+  return parseFloat(normalized);
+}
+
+/**
+ * Find all active cues at the given time.
+ * Assumes cues are sorted by startTime (VTT spec requires this).
+ */
+export function getActiveCues(cues: VttCue[], currentTime: number): VttCue[] {
+  return cues.filter(
+    (cue) => currentTime >= cue.startTime && currentTime < cue.endTime
+  );
+}
+
+/**
+ * Given a cue with word segments and the current playback time,
+ * return which words are "spoken" (their startTime <= currentTime)
+ * and which are "upcoming" (their startTime > currentTime).
+ */
+export function getActiveWords(
+  cue: VttCue,
+  currentTime: number
+): { text: string; spoken: boolean }[] {
+  if (!cue.words || cue.words.length === 0) {
+    return [{ text: cue.text, spoken: true }];
+  }
+  return cue.words.map((word) => ({
+    text: word.text,
+    spoken: currentTime >= word.startTime,
+  }));
+}