chore: bump version to 0.2.43 [skip ci]

Previously only the main sidecar binary got chmod 755. Now all files
in the extraction directory get execute permissions — covers ffmpeg,
ffprobe, and any other bundled binaries. Applied in three places:
- sidecar/mod.rs: after local extraction
- commands/sidecar.rs: after download extraction
- commands/media.rs: removed single-file fix (now handled globally)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

docs/USER_GUIDE.md

@@ -26,10 +26,13 @@ The sidecar only needs to be downloaded once. Updates are detected automatically
 
 ## Basic Workflow
 
-### 1. Import Audio
+### 1. Import Audio or Video
 
 - Click **Import Audio** or press **Ctrl+O** (Cmd+O on Mac)
-- Supported formats: MP3, WAV, FLAC, OGG, M4A, AAC, WMA, MP4, MKV, AVI, MOV, WebM
+- **Audio formats:** MP3, WAV, FLAC, OGG, M4A, AAC, WMA
+- **Video formats:** MP4, MKV, AVI, MOV, WebM — audio is automatically extracted
+
+> **Note:** Video file import requires [FFmpeg](#installing-ffmpeg) to be installed on your system.
 
 ### 2. Transcribe
 
@@ -181,8 +184,42 @@ If you prefer cloud-based AI:
 
 ---
 
+## Installing FFmpeg
+
+FFmpeg is required for importing video files (MP4, MKV, AVI, etc.). It's used to extract the audio track before transcription.
+
+**Windows:**
+```
+winget install ffmpeg
+```
+Or download from [ffmpeg.org/download.html](https://ffmpeg.org/download.html) and add to your PATH.
+
+**macOS:**
+```
+brew install ffmpeg
+```
+
+**Linux (Debian/Ubuntu):**
+```
+sudo apt install ffmpeg
+```
+
+**Linux (Fedora/RHEL):**
+```
+sudo dnf install ffmpeg
+```
+
+After installing, restart Voice to Notes. FFmpeg is not needed for audio-only files (MP3, WAV, FLAC, etc.).
+
+---
+
 ## Troubleshooting
 
+### Video import fails / "FFmpeg not found"
+- Install FFmpeg using the instructions above
+- Make sure `ffmpeg` is in your system PATH
+- Restart Voice to Notes after installing
+
 ### Transcription is slow
 - Use a smaller model (tiny or base)
 - If you have an NVIDIA GPU, select CUDA in Settings > Transcription > Device

package.json

@@ -1,6 +1,6 @@
 {
   "name": "voice-to-notes",
-  "version": "0.2.28",
+  "version": "0.2.43",
   "description": "Desktop app for transcribing audio/video with speaker identification",
   "type": "module",
   "scripts": {

python/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "voice-to-notes"
-version = "1.0.11"
+version = "1.0.13"
 description = "Python sidecar for Voice to Notes — transcription, diarization, and AI services"
 requires-python = ">=3.11"
 license = "MIT"

python/voice_to_notes/services/diarize.py

@@ -41,14 +41,23 @@ def _patch_pyannote_audio() -> None:
         import torch
         from pyannote.audio.core.io import Audio
 
+        # Cache loaded audio to avoid re-reading the entire file for every crop call.
+        # For a 3-hour file, crop is called 1000+ times — without caching, each call
+        # reads ~345MB from disk.
+        _audio_cache: dict[str, tuple] = {}
+
         def _sf_load(audio_path: str) -> tuple:
-            """Load audio via soundfile, return (channels, samples) tensor + sample_rate."""
+            """Load audio via soundfile with caching."""
-            data, sample_rate = sf.read(str(audio_path), dtype="float32")
+            key = str(audio_path)
+            if key in _audio_cache:
+                return _audio_cache[key]
+            data, sample_rate = sf.read(key, dtype="float32")
             waveform = torch.from_numpy(np.array(data))
             if waveform.ndim == 1:
                 waveform = waveform.unsqueeze(0)
             else:
                 waveform = waveform.T
+            _audio_cache[key] = (waveform, sample_rate)
             return waveform, sample_rate
 
         def _soundfile_call(self, file: dict) -> tuple:
@@ -56,7 +65,7 @@ def _patch_pyannote_audio() -> None:
             return _sf_load(file["audio"])
 
         def _soundfile_crop(self, file: dict, segment, **kwargs) -> tuple:
-            """Replacement for Audio.crop — load full file then slice.
+            """Replacement for Audio.crop — load file once (cached) then slice.
 
             Pads short segments with zeros to match the expected duration,
             which pyannote requires for batched embedding extraction.
@@ -279,13 +288,20 @@ class DiarizeService:
         thread.start()
 
         elapsed = 0.0
-        estimated_total = max(audio_duration_sec * 0.5, 30.0) if audio_duration_sec else 120.0
+        estimated_total = max(audio_duration_sec * 0.8, 30.0) if audio_duration_sec else 120.0
-        while not done_event.wait(timeout=2.0):
+        duration_str = ""
-            elapsed += 2.0
+        if audio_duration_sec and audio_duration_sec > 600:
+            mins = int(audio_duration_sec / 60)
+            duration_str = f" ({mins}min audio, this may take a while)"
+        while not done_event.wait(timeout=5.0):
+            elapsed += 5.0
             pct = min(20 + int((elapsed / estimated_total) * 65), 85)
+            elapsed_min = int(elapsed / 60)
+            elapsed_sec = int(elapsed % 60)
+            time_str = f"{elapsed_min}m{elapsed_sec:02d}s" if elapsed_min > 0 else f"{int(elapsed)}s"
             write_message(progress_message(
                 request_id, pct, "diarizing",
-                f"Analyzing speakers ({int(elapsed)}s elapsed)..."))
+                f"Analyzing speakers ({time_str} elapsed){duration_str}"))
 
         thread.join()
 

python/voice_to_notes/services/transcribe.py

@@ -113,17 +113,22 @@ class TranscribeService:
         compute_type: str = "int8",
         language: str | None = None,
         on_segment: Callable[[SegmentResult, int], None] | None = None,
+        chunk_label: str | None = None,
     ) -> TranscriptionResult:
         """Transcribe an audio file with word-level timestamps.
 
         Sends progress messages via IPC during processing.
+        If chunk_label is set (e.g. "chunk 3/12"), messages are prefixed with it.
         """
-        # Stage: loading model
+        prefix = f"{chunk_label}: " if chunk_label else ""
-        write_message(progress_message(request_id, 0, "loading_model", f"Loading {model_name}..."))
+
+        # Stage: loading model (skip for chunks after the first — model already loaded)
+        if not chunk_label:
+            write_message(progress_message(request_id, 0, "loading_model", f"Loading {model_name}..."))
         model = self._ensure_model(model_name, device, compute_type)
 
         # Stage: transcribing
-        write_message(progress_message(request_id, 10, "transcribing", "Starting transcription..."))
+        write_message(progress_message(request_id, 10, "transcribing", f"{prefix}Starting transcription..."))
 
         start_time = time.time()
         segments_iter, info = model.transcribe(
@@ -176,7 +181,7 @@ class TranscribeService:
                     request_id,
                     progress_pct,
                     "transcribing",
-                    f"Transcribing segment {segment_count} ({progress_pct}% of audio)...",
+                    f"{prefix}Transcribing segment {segment_count} ({progress_pct}% of audio)...",
                 )
             )
 
@@ -271,6 +276,7 @@ class TranscribeService:
                 chunk_result = self.transcribe(
                     request_id, tmp.name, model_name, device,
                     compute_type, language, on_segment=chunk_on_segment,
+                    chunk_label=f"Chunk {chunk_idx + 1}/{num_chunks}",
                 )
 
                 # Offset timestamps and merge

src-tauri/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "voice-to-notes"
-version = "0.2.28"
+version = "0.2.43"
 description = "Voice to Notes — desktop transcription with speaker identification"
 authors = ["Voice to Notes Contributors"]
 license = "MIT"

src-tauri/src/commands/media.rs

@@ -0,0 +1,124 @@
+use std::path::PathBuf;
+use std::process::Command;
+
+#[cfg(target_os = "windows")]
+use std::os::windows::process::CommandExt;
+
+/// Extract audio from a video file to a WAV file using ffmpeg.
+/// Returns the path to the extracted audio file.
+#[tauri::command]
+pub fn extract_audio(file_path: String, output_path: Option<String>) -> Result<String, String> {
+    let input = PathBuf::from(&file_path);
+    if !input.exists() {
+        return Err(format!("File not found: {}", file_path));
+    }
+
+    // Use provided output path, or fall back to a temp WAV file
+    let stem = input.file_stem().unwrap_or_default().to_string_lossy();
+    let output = match output_path {
+        Some(ref p) => PathBuf::from(p),
+        None => std::env::temp_dir().join(format!("{stem}_audio.wav")),
+    };
+
+    eprintln!(
+        "[media] Extracting audio: {} -> {}",
+        input.display(),
+        output.display()
+    );
+
+    // Find ffmpeg — check sidecar extract dir first, then system PATH
+    let ffmpeg = find_ffmpeg().ok_or("ffmpeg not found. Install ffmpeg or ensure it's in PATH.")?;
+
+    let mut cmd = Command::new(&ffmpeg);
+    cmd.args([
+            "-y",             // Overwrite output
+            "-i",
+            &file_path,
+            "-vn",            // No video
+            "-acodec",
+            "pcm_s16le",      // WAV PCM 16-bit
+            "-ar",
+            "22050",          // 22kHz mono for better playback quality
+            "-ac",
+            "1",              // Mono
+        ])
+        .arg(output.to_str().unwrap())
+        .stdout(std::process::Stdio::null())
+        .stderr(std::process::Stdio::piped());
+
+    // Hide the console window on Windows (CREATE_NO_WINDOW = 0x08000000)
+    #[cfg(target_os = "windows")]
+    cmd.creation_flags(0x08000000);
+
+    let status = cmd
+        .status()
+        .map_err(|e| format!("Failed to run ffmpeg: {e}"))?;
+
+    if !status.success() {
+        return Err(format!("ffmpeg exited with status {status}"));
+    }
+
+    if !output.exists() {
+        return Err("ffmpeg completed but output file not found".to_string());
+    }
+
+    eprintln!("[media] Audio extracted successfully");
+    Ok(output.to_string_lossy().to_string())
+}
+
+#[tauri::command]
+pub fn check_file_exists(path: String) -> bool {
+    std::path::Path::new(&path).exists()
+}
+
+#[tauri::command]
+pub fn copy_file(src: String, dst: String) -> Result<(), String> {
+    std::fs::copy(&src, &dst).map_err(|e| format!("Failed to copy file: {e}"))?;
+    Ok(())
+}
+
+#[tauri::command]
+pub fn create_dir(path: String) -> Result<(), String> {
+    std::fs::create_dir_all(&path).map_err(|e| format!("Failed to create directory: {e}"))?;
+    Ok(())
+}
+
+/// Find ffmpeg binary — check sidecar directory first, then system PATH.
+fn find_ffmpeg() -> Option<String> {
+    // Check sidecar extract dir (ffmpeg is bundled with the sidecar)
+    if let Some(data_dir) = crate::sidecar::DATA_DIR.get() {
+        // Read sidecar version to find the right directory
+        let version_file = data_dir.join("sidecar-version.txt");
+        if let Ok(version) = std::fs::read_to_string(&version_file) {
+            let version = version.trim();
+            let sidecar_dir = data_dir.join(format!("sidecar-{version}"));
+            let ffmpeg_name = if cfg!(target_os = "windows") {
+                "ffmpeg.exe"
+            } else {
+                "ffmpeg"
+            };
+            let ffmpeg_path = sidecar_dir.join(ffmpeg_name);
+            if ffmpeg_path.exists() {
+                return Some(ffmpeg_path.to_string_lossy().to_string());
+            }
+        }
+    }
+
+    // Fall back to system PATH
+    let ffmpeg_name = if cfg!(target_os = "windows") {
+        "ffmpeg.exe"
+    } else {
+        "ffmpeg"
+    };
+    if Command::new(ffmpeg_name)
+        .arg("-version")
+        .stdout(std::process::Stdio::null())
+        .stderr(std::process::Stdio::null())
+        .status()
+        .is_ok()
+    {
+        return Some(ffmpeg_name.to_string());
+    }
+
+    None
+}

src-tauri/src/commands/mod.rs

@@ -1,5 +1,6 @@
 pub mod ai;
 pub mod export;
+pub mod media;
 pub mod project;
 pub mod settings;
 pub mod sidecar;

src-tauri/src/commands/project.rs

@@ -12,7 +12,12 @@ use crate::state::AppState;
 pub struct ProjectFile {
     pub version: u32,
     pub name: String,
-    pub audio_file: String,
+    #[serde(default)]
+    pub audio_file: Option<String>,
+    #[serde(default)]
+    pub source_file: Option<String>,
+    #[serde(default)]
+    pub audio_wav: Option<String>,
     pub created_at: String,
     pub segments: Vec<ProjectFileSegment>,
     pub speakers: Vec<ProjectFileSpeaker>,

src-tauri/src/commands/sidecar.rs

@@ -197,15 +197,21 @@ pub async fn download_sidecar(app: AppHandle, variant: String) -> Result<(), Str
     let extract_dir = data_dir.join(format!("sidecar-{}", sidecar_version));
     SidecarManager::extract_zip(&zip_path, &extract_dir)?;
 
-    // Make the binary executable on Unix
+    // Make all binaries executable on Unix (sidecar, ffmpeg, ffprobe, etc.)
     #[cfg(unix)]
     {
         use std::os::unix::fs::PermissionsExt;
-        let binary_path = extract_dir.join("voice-to-notes-sidecar");
+        if let Ok(entries) = std::fs::read_dir(&extract_dir) {
-        if let Ok(meta) = std::fs::metadata(&binary_path) {
+            for entry in entries.flatten() {
-            let mut perms = meta.permissions();
+                let path = entry.path();
-            perms.set_mode(0o755);
+                if path.is_file() {
-            let _ = std::fs::set_permissions(&binary_path, perms);
+                    if let Ok(meta) = std::fs::metadata(&path) {
+                        let mut perms = meta.permissions();
+                        perms.set_mode(0o755);
+                        let _ = std::fs::set_permissions(&path, perms);
+                    }
+                }
+            }
         }
     }
 

src-tauri/src/lib.rs

@@ -9,6 +9,7 @@ use tauri::Manager;
 
 use commands::ai::{ai_chat, ai_configure, ai_list_providers};
 use commands::export::export_transcript;
+use commands::media::{check_file_exists, copy_file, create_dir, extract_audio};
 use commands::project::{
     create_project, delete_project, get_project, list_projects, load_project_file,
     load_project_transcript, save_project_file, save_project_transcript, update_segment,
@@ -73,6 +74,10 @@ pub fn run() {
             check_sidecar_update,
             log_frontend,
             toggle_devtools,
+            extract_audio,
+            check_file_exists,
+            copy_file,
+            create_dir,
         ])
         .run(tauri::generate_context!())
         .expect("error while running tauri application");

src-tauri/src/sidecar/mod.rs

@@ -113,14 +113,21 @@ impl SidecarManager {
             ));
         }
 
-        // Make executable on Unix
+        // Make all binaries executable on Unix (sidecar, ffmpeg, ffprobe, etc.)
         #[cfg(unix)]
         {
             use std::os::unix::fs::PermissionsExt;
-            if let Ok(meta) = std::fs::metadata(&binary_path) {
+            if let Ok(entries) = std::fs::read_dir(&extract_dir) {
-                let mut perms = meta.permissions();
+                for entry in entries.flatten() {
-                perms.set_mode(0o755);
+                    let path = entry.path();
-                let _ = std::fs::set_permissions(&binary_path, perms);
+                    if path.is_file() {
+                        if let Ok(meta) = std::fs::metadata(&path) {
+                            let mut perms = meta.permissions();
+                            perms.set_mode(0o755);
+                            let _ = std::fs::set_permissions(&path, perms);
+                        }
+                    }
+                }
             }
         }
 

src-tauri/tauri.conf.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://schema.tauri.app/config/2",
   "productName": "Voice to Notes",
-  "version": "0.2.28",
+  "version": "0.2.43",
   "identifier": "com.voicetonotes.app",
   "build": {
     "beforeDevCommand": "npm run dev",

src/lib/components/AIChatPanel.svelte

@@ -1,7 +1,7 @@
 <script lang="ts">
   import { invoke } from '@tauri-apps/api/core';
   import { segments, speakers } from '$lib/stores/transcript';
-  import { settings } from '$lib/stores/settings';
+  import { settings, configureAIProvider } from '$lib/stores/settings';
 
   interface ChatMessage {
     role: 'user' | 'assistant';
@@ -45,22 +45,12 @@
       }));
 
       // Ensure the provider is configured with current credentials before chatting
-      const s = $settings;
+      await configureAIProvider($settings);
-      const configMap: Record<string, Record<string, string>> = {
-        openai: { api_key: s.openai_api_key, model: s.openai_model },
-        anthropic: { api_key: s.anthropic_api_key, model: s.anthropic_model },
-        litellm: { api_key: s.litellm_api_key, api_base: s.litellm_api_base, model: s.litellm_model },
-        local: { model: s.local_model_path, base_url: 'http://localhost:8080' },
-      };
-      const config = configMap[s.ai_provider];
-      if (config) {
-        await invoke('ai_configure', { provider: s.ai_provider, config });
-      }
 
       const result = await invoke<{ response: string }>('ai_chat', {
         messages: chatMessages,
         transcriptContext: getTranscriptContext(),
-        provider: s.ai_provider,
+        provider: $settings.ai_provider,
       });
 
       messages = [...messages, { role: 'assistant', content: result.response }];

src/lib/components/ProgressOverlay.svelte

@@ -4,9 +4,25 @@
     percent?: number;
     stage?: string;
     message?: string;
+    onCancel?: () => void;
   }
 
-  let { visible = false, percent = 0, stage = '', message = '' }: Props = $props();
+  let { visible = false, percent = 0, stage = '', message = '', onCancel }: Props = $props();
+
+  let showConfirm = $state(false);
+
+  function handleCancelClick() {
+    showConfirm = true;
+  }
+
+  function confirmCancel() {
+    showConfirm = false;
+    onCancel?.();
+  }
+
+  function dismissCancel() {
+    showConfirm = false;
+  }
 
   // Pipeline steps in order
   const pipelineSteps = [
@@ -89,6 +105,20 @@
 
       <p class="status-text">{message || 'Please wait...'}</p>
       <p class="hint-text">This may take several minutes for large files</p>
+
+      {#if onCancel && !showConfirm}
+        <button class="cancel-btn" onclick={handleCancelClick}>Cancel</button>
+      {/if}
+
+      {#if showConfirm}
+        <div class="confirm-box">
+          <p class="confirm-text">Processing is incomplete. If you cancel now, the transcription will need to be started over.</p>
+          <div class="confirm-actions">
+            <button class="confirm-keep" onclick={dismissCancel}>Continue Processing</button>
+            <button class="confirm-cancel" onclick={confirmCancel}>Cancel Processing</button>
+          </div>
+        </div>
+      {/if}
     </div>
   </div>
 {/if}
@@ -174,4 +204,62 @@
     font-size: 0.75rem;
     color: #555;
   }
+  .cancel-btn {
+    margin-top: 1.25rem;
+    width: 100%;
+    padding: 0.5rem;
+    background: none;
+    border: 1px solid #4a5568;
+    color: #999;
+    border-radius: 6px;
+    cursor: pointer;
+    font-size: 0.85rem;
+  }
+  .cancel-btn:hover {
+    color: #e0e0e0;
+    border-color: #e94560;
+  }
+  .confirm-box {
+    margin-top: 1.25rem;
+    padding: 0.75rem;
+    background: rgba(233, 69, 96, 0.08);
+    border: 1px solid #e94560;
+    border-radius: 6px;
+  }
+  .confirm-text {
+    margin: 0 0 0.75rem;
+    font-size: 0.8rem;
+    color: #e0e0e0;
+    line-height: 1.4;
+  }
+  .confirm-actions {
+    display: flex;
+    gap: 0.5rem;
+  }
+  .confirm-keep {
+    flex: 1;
+    padding: 0.4rem;
+    background: #0f3460;
+    border: 1px solid #4a5568;
+    color: #e0e0e0;
+    border-radius: 4px;
+    cursor: pointer;
+    font-size: 0.8rem;
+  }
+  .confirm-keep:hover {
+    background: #1a4a7a;
+  }
+  .confirm-cancel {
+    flex: 1;
+    padding: 0.4rem;
+    background: #e94560;
+    border: none;
+    color: white;
+    border-radius: 4px;
+    cursor: pointer;
+    font-size: 0.8rem;
+  }
+  .confirm-cancel:hover {
+    background: #d63851;
+  }
 </style>

src/lib/components/WaveformPlayer.svelte

@@ -57,6 +57,12 @@
       isReady = false;
     });
 
+    wavesurfer.on('error', (err: Error) => {
+      console.error('[voice-to-notes] WaveSurfer error:', err);
+      isLoading = false;
+      loadError = 'Failed to load audio';
+    });
+
     if (audioUrl) {
       loadAudio(audioUrl);
     }

src/lib/stores/settings.ts

@@ -52,23 +52,27 @@ export async function loadSettings(): Promise<void> {
   }
 }
 
-export async function saveSettings(s: AppSettings): Promise<void> {
+export async function configureAIProvider(s: AppSettings): Promise<void> {
-  settings.set(s);
-  await invoke('save_settings', { settings: s });
-
-  // Configure the AI provider in the Python sidecar
   const configMap: Record<string, Record<string, string>> = {
     openai: { api_key: s.openai_api_key, model: s.openai_model },
     anthropic: { api_key: s.anthropic_api_key, model: s.anthropic_model },
     litellm: { api_key: s.litellm_api_key, api_base: s.litellm_api_base, model: s.litellm_model },
-    local: { model: s.ollama_model, base_url: s.ollama_url + '/v1' },
+    local: { model: s.ollama_model, base_url: s.ollama_url.replace(/\/+$/, '') + '/v1' },
   };
   const config = configMap[s.ai_provider];
   if (config) {
     try {
       await invoke('ai_configure', { provider: s.ai_provider, config });
     } catch {
-      // Sidecar may not be running yet — provider will be configured on first use
+      // Sidecar may not be running yet
     }
   }
 }
+
+export async function saveSettings(s: AppSettings): Promise<void> {
+  settings.set(s);
+  await invoke('save_settings', { settings: s });
+
+  // Configure the AI provider in the Python sidecar
+  await configureAIProvider(s);
+}

src/routes/+page.svelte

@@ -10,7 +10,7 @@
   import SettingsModal from '$lib/components/SettingsModal.svelte';
   import SidecarSetup from '$lib/components/SidecarSetup.svelte';
   import { segments, speakers } from '$lib/stores/transcript';
-  import { settings, loadSettings } from '$lib/stores/settings';
+  import { settings, loadSettings, configureAIProvider } from '$lib/stores/settings';
   import type { Segment, Speaker } from '$lib/types/transcript';
   import { onMount, tick } from 'svelte';
 
@@ -31,7 +31,9 @@
   // Project management state
   let currentProjectPath = $state<string | null>(null);
   let currentProjectName = $state('');
+  let projectIsV2 = $state(false);
   let audioFilePath = $state('');
+  let audioWavPath = $state('');
 
   async function checkSidecar() {
     try {
@@ -54,6 +56,7 @@
 
   function handleSidecarSetupComplete() {
     sidecarReady = true;
+    configureAIProvider($settings);
     checkSidecarUpdate();
   }
 
@@ -71,6 +74,7 @@
     });
     checkSidecar().then(() => {
       if (sidecarReady) {
+        configureAIProvider($settings);
         checkSidecarUpdate();
       }
     });
@@ -117,25 +121,32 @@
     };
   });
   let isTranscribing = $state(false);
+  let transcriptionCancelled = $state(false);
   let transcriptionProgress = $state(0);
   let transcriptionStage = $state('');
   let transcriptionMessage = $state('');
+  let extractingAudio = $state(false);
+
+  function handleCancelProcessing() {
+    transcriptionCancelled = true;
+    isTranscribing = false;
+    transcriptionProgress = 0;
+    transcriptionStage = '';
+    transcriptionMessage = '';
+    // Clear any partial results
+    segments.set([]);
+    speakers.set([]);
+  }
 
   // Speaker color palette for auto-assignment
   const speakerColors = ['#e94560', '#4ecdc4', '#ffe66d', '#a8e6cf', '#ff8b94', '#c7ceea', '#ffd93d', '#6bcb77'];
 
-  async function saveProject() {
+  function buildProjectData(projectName: string) {
-    const defaultName = currentProjectName || 'Untitled';
+    return {
-    const outputPath = await save({
+      version: 2,
-      defaultPath: `${defaultName}.vtn`,
+      name: projectName,
-      filters: [{ name: 'Voice to Notes Project', extensions: ['vtn'] }],
+      source_file: audioFilePath,
-    });
+      audio_wav: 'audio.wav',
-    if (!outputPath) return;
-
-    const projectData = {
-      version: 1,
-      name: outputPath.split(/[\\/]/).pop()?.replace('.vtn', '') || defaultName,
-      audio_file: audioFilePath,
       created_at: new Date().toISOString(),
       segments: $segments.map(seg => {
         const speaker = $speakers.find(s => s.id === seg.speaker_id);
@@ -159,17 +170,75 @@
         color: s.color || '#e94560',
       })),
     };
+  }
+
+  /** Save to a specific folder — creates .vtn + audio.wav inside it. */
+  async function saveToFolder(folderPath: string): Promise<boolean> {
+    const projectName = folderPath.split(/[\\/]/).pop() || currentProjectName || 'Untitled';
+    const vtnPath = `${folderPath}/${projectName}.vtn`;
+    const wavPath = `${folderPath}/audio.wav`;
+    const projectData = buildProjectData(projectName);
 
     try {
-      await invoke('save_project_file', { path: outputPath, project: projectData });
+      await invoke('create_dir', { path: folderPath });
-      currentProjectPath = outputPath;
+      if (audioWavPath && audioWavPath !== wavPath) {
-      currentProjectName = projectData.name;
+        await invoke('copy_file', { src: audioWavPath, dst: wavPath });
+        audioWavPath = wavPath;
+      }
+      await invoke('save_project_file', { path: vtnPath, project: projectData });
+      currentProjectPath = vtnPath;
+      currentProjectName = projectName;
+      projectIsV2 = true;
+      return true;
     } catch (err) {
       console.error('Failed to save project:', err);
       alert(`Failed to save: ${err}`);
+      return false;
     }
   }
 
+  async function saveProject() {
+    // Already saved as v2 folder — save in place
+    if (currentProjectPath && projectIsV2) {
+      const folderPath = currentProjectPath.replace(/[\\/][^\\/]+$/, '');
+      await saveToFolder(folderPath);
+      return;
+    }
+
+    // V1 project opened — migrate to folder structure
+    if (currentProjectPath && !projectIsV2) {
+      const oldVtnDir = currentProjectPath.replace(/[\\/][^\\/]+$/, '');
+      const projectName = currentProjectPath.split(/[\\/]/).pop()?.replace(/\.vtn$/i, '') || 'Untitled';
+      const folderPath = `${oldVtnDir}/${projectName}`;
+      const success = await saveToFolder(folderPath);
+      if (success) {
+        // Optionally remove the old .vtn file
+        try {
+          // Leave old file — user can delete manually
+        } catch {}
+      }
+      return;
+    }
+
+    // Never saved — pick a folder
+    await saveProjectAs();
+  }
+
+  async function saveProjectAs() {
+    // Use save dialog so the user can type a new project name.
+    // The chosen path is treated as the project folder (created if needed).
+    const defaultName = currentProjectName || 'Untitled';
+    const chosenPath = await save({
+      defaultPath: defaultName,
+      title: 'Save Project — enter a project name',
+    });
+    if (!chosenPath) return;
+
+    // Strip any file extension the user may have typed (e.g. ".vtn")
+    const folderPath = chosenPath.replace(/\.[^.\\/]+$/, '');
+    await saveToFolder(folderPath);
+  }
+
   async function openProject() {
     const filePath = await open({
       filters: [{ name: 'Voice to Notes Project', extensions: ['vtn'] }],
@@ -179,9 +248,11 @@
 
     try {
       const project = await invoke<{
-        version: number;
+        version?: number;
         name: string;
-        audio_file: string;
+        audio_file?: string;
+        source_file?: string;
+        audio_wav?: string;
         segments: Array<{
           text: string;
           start_ms: number;
@@ -231,10 +302,135 @@
       }));
       segments.set(newSegments);
 
-      // Load audio
+      // Determine the directory the .vtn file is in
-      audioFilePath = project.audio_file;
+      const vtnDir = (filePath as string).replace(/[\\/][^\\/]+$/, '');
-      audioUrl = convertFileSrc(project.audio_file);
+      const version = project.version ?? 1;
-      waveformPlayer?.loadAudio(audioUrl);
+      projectIsV2 = version >= 2;
+
+      // Resolve audio for wavesurfer playback
+      if (version >= 2) {
+        // Version 2: audio_wav is relative to the .vtn directory, source_file is the original import path
+        audioFilePath = project.source_file || '';
+        const wavRelative = project.audio_wav || 'audio.wav';
+        const resolvedWav = `${vtnDir}/${wavRelative}`;
+
+        const wavExists = await invoke<boolean>('check_file_exists', { path: resolvedWav });
+        if (wavExists) {
+          audioWavPath = resolvedWav;
+          audioUrl = convertFileSrc(resolvedWav);
+          waveformPlayer?.loadAudio(audioUrl);
+        } else {
+          // WAV missing — try re-extracting from the original source file
+          const sourceExists = audioFilePath ? await invoke<boolean>('check_file_exists', { path: audioFilePath }) : false;
+          if (sourceExists) {
+            extractingAudio = true;
+            await tick();
+            try {
+              const outputPath = `${vtnDir}/${wavRelative}`;
+              const wavPath = await invoke<string>('extract_audio', { filePath: audioFilePath, outputPath });
+              audioWavPath = wavPath;
+              audioUrl = convertFileSrc(wavPath);
+              waveformPlayer?.loadAudio(audioUrl);
+            } catch (err) {
+              console.error('Failed to re-extract audio:', err);
+              alert(`Failed to re-extract audio: ${err}`);
+            } finally {
+              extractingAudio = false;
+            }
+          } else {
+            // Both missing — ask user to locate the file
+            const shouldRelink = confirm(
+              'The audio file for this project could not be found.\n\n' +
+              `Original source: ${audioFilePath || '(unknown)'}\n\n` +
+              'Would you like to locate the file?'
+            );
+            if (shouldRelink) {
+              const newPath = await open({
+                multiple: false,
+                filters: [{
+                  name: 'Audio/Video',
+                  extensions: ['mp3', 'wav', 'flac', 'ogg', 'm4a', 'aac', 'wma',
+                               'mp4', 'mkv', 'avi', 'mov', 'webm'],
+                }],
+              });
+              if (newPath) {
+                audioFilePath = newPath;
+                extractingAudio = true;
+                await tick();
+                try {
+                  const outputPath = `${vtnDir}/${wavRelative}`;
+                  const wavPath = await invoke<string>('extract_audio', { filePath: newPath, outputPath });
+                  audioWavPath = wavPath;
+                  audioUrl = convertFileSrc(wavPath);
+                  waveformPlayer?.loadAudio(audioUrl);
+                } catch (err) {
+                  console.error('Failed to extract audio from re-linked file:', err);
+                  alert(`Failed to extract audio: ${err}`);
+                } finally {
+                  extractingAudio = false;
+                }
+              }
+            }
+          }
+        }
+      } else {
+        // Version 1 (legacy): audio_file is the source path
+        const sourceFile = project.audio_file || '';
+        audioFilePath = sourceFile;
+
+        const sourceExists = sourceFile ? await invoke<boolean>('check_file_exists', { path: sourceFile }) : false;
+        if (sourceExists) {
+          // Extract WAV next to the .vtn file for playback
+          extractingAudio = true;
+          await tick();
+          try {
+            const outputPath = `${vtnDir}/audio.wav`;
+            const wavPath = await invoke<string>('extract_audio', { filePath: sourceFile, outputPath });
+            audioWavPath = wavPath;
+            audioUrl = convertFileSrc(wavPath);
+            waveformPlayer?.loadAudio(audioUrl);
+          } catch (err) {
+            console.error('Failed to extract audio:', err);
+            alert(`Failed to extract audio: ${err}`);
+          } finally {
+            extractingAudio = false;
+          }
+        } else {
+          // Source missing — ask user to locate the file
+          const shouldRelink = confirm(
+            'The audio file for this project could not be found.\n\n' +
+            `Original path: ${sourceFile || '(unknown)'}\n\n` +
+            'Would you like to locate the file?'
+          );
+          if (shouldRelink) {
+            const newPath = await open({
+              multiple: false,
+              filters: [{
+                name: 'Audio/Video',
+                extensions: ['mp3', 'wav', 'flac', 'ogg', 'm4a', 'aac', 'wma',
+                             'mp4', 'mkv', 'avi', 'mov', 'webm'],
+              }],
+            });
+            if (newPath) {
+              audioFilePath = newPath;
+              extractingAudio = true;
+              await tick();
+              try {
+                const outputPath = `${vtnDir}/audio.wav`;
+                const wavPath = await invoke<string>('extract_audio', { filePath: newPath, outputPath });
+                audioWavPath = wavPath;
+                audioUrl = convertFileSrc(wavPath);
+                waveformPlayer?.loadAudio(audioUrl);
+              } catch (err) {
+                console.error('Failed to extract audio from re-linked file:', err);
+                alert(`Failed to extract audio: ${err}`);
+              } finally {
+                extractingAudio = false;
+              }
+            }
+          }
+        }
+      }
 
       currentProjectPath = filePath as string;
       currentProjectName = project.name;
@@ -265,9 +461,35 @@
     });
     if (!filePath) return;
 
-    // Track the original file path and convert to asset URL for wavesurfer
+    // Always extract audio to WAV for wavesurfer playback
+    extractingAudio = true;
+    await tick();
+    try {
+      const wavPath = await invoke<string>('extract_audio', { filePath });
+      audioWavPath = wavPath;
+    } catch (err) {
+      console.error('[voice-to-notes] Failed to extract audio:', err);
+      const msg = String(err);
+      if (msg.includes('ffmpeg not found')) {
+        alert(
+          'FFmpeg is required to extract audio.\n\n' +
+          'Install FFmpeg:\n' +
+          '  Windows: winget install ffmpeg\n' +
+          '  macOS: brew install ffmpeg\n' +
+          '  Linux: sudo apt install ffmpeg\n\n' +
+          'Then restart Voice to Notes and try again.'
+        );
+      } else {
+        alert(`Failed to extract audio: ${msg}`);
+      }
+      return;
+    } finally {
+      extractingAudio = false;
+    }
+
+    // Track the original file path for the sidecar (it does its own conversion)
     audioFilePath = filePath;
-    audioUrl = convertFileSrc(filePath);
+    audioUrl = convertFileSrc(audioWavPath);
     waveformPlayer?.loadAudio(audioUrl);
 
     // Clear previous results
@@ -276,6 +498,7 @@
 
     // Start pipeline (transcription + diarization)
     isTranscribing = true;
+    transcriptionCancelled = false;
     transcriptionProgress = 0;
     transcriptionStage = 'Starting...';
     transcriptionMessage = 'Initializing pipeline...';
@@ -386,6 +609,9 @@
         numSpeakers: $settings.num_speakers && $settings.num_speakers > 0 ? $settings.num_speakers : undefined,
       });
 
+      // If cancelled while processing, discard results
+      if (transcriptionCancelled) return;
+
       // Create speaker entries from pipeline result
       const newSpeakers: Speaker[] = (result.speakers || []).map((label, idx) => ({
         id: `speaker-${idx}`,
@@ -524,7 +750,10 @@
       </button>
       {#if $segments.length > 0}
         <button class="settings-btn" onclick={saveProject}>
-          Save Project
+          Save
+        </button>
+        <button class="settings-btn" onclick={saveProjectAs}>
+          Save As
         </button>
       {/if}
       <button class="import-btn" onclick={handleFileImport} disabled={isTranscribing}>
@@ -573,8 +802,18 @@
     percent={transcriptionProgress}
     stage={transcriptionStage}
     message={transcriptionMessage}
+    onCancel={handleCancelProcessing}
   />
 
+  {#if extractingAudio}
+    <div class="extraction-overlay">
+      <div class="extraction-card">
+        <div class="extraction-spinner"></div>
+        <p>Extracting audio...</p>
+      </div>
+    </div>
+  {/if}
+
   <SettingsModal
     visible={showSettings}
     onClose={() => showSettings = false}
@@ -781,4 +1020,39 @@
   .update-dismiss:hover {
     color: #e0e0e0;
   }
+
+  /* Audio extraction overlay */
+  .extraction-overlay {
+    position: fixed;
+    inset: 0;
+    background: rgba(0, 0, 0, 0.8);
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    z-index: 9999;
+  }
+  .extraction-card {
+    background: #16213e;
+    padding: 2rem 2.5rem;
+    border-radius: 12px;
+    color: #e0e0e0;
+    border: 1px solid #2a3a5e;
+    box-shadow: 0 8px 32px rgba(0, 0, 0, 0.5);
+    display: flex;
+    flex-direction: column;
+    align-items: center;
+    gap: 1rem;
+  }
+  .extraction-card p {
+    margin: 0;
+    font-size: 1rem;
+  }
+  .extraction-spinner {
+    width: 32px;
+    height: 32px;
+    border: 3px solid #2a3a5e;
+    border-top-color: #e94560;
+    border-radius: 50%;
+    animation: spin 0.8s linear infinite;
+  }
 </style>