chore: bump sidecar version to 1.0.12 [skip ci]

- Cache loaded audio in _sf_load() — previously the entire WAV file was
  re-read from disk for every 10s crop call. For a 3-hour file with
  1000+ chunks, this meant ~345GB of disk reads. Now read once, cached.
- Better progress messages for long files: show elapsed time in m:ss
  format, warn "(180min audio, this may take a while)" for files >10min
- Increased progress poll interval from 2s to 5s (less noise)
- Better time estimate: use 0.8x audio duration (was 0.5x)

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": "0.2.27",
+  "version": "0.2.32",
   "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 = "1.0.10"
+version = "1.0.12"
 description = "Python sidecar for Voice to Notes — transcription, diarization, and AI services"
 requires-python = ">=3.11"
 license = "MIT"

python/voice_to_notes/ipc/handlers.py

@@ -254,15 +254,15 @@ def make_ai_chat_handler() -> HandlerFunc:
             )
 
         if action == "configure":
-            # Re-create a provider with custom settings
+            # Re-create a provider with custom settings and set it active
             provider_name = payload.get("provider", "")
             config = payload.get("config", {})
             if provider_name == "local":
                 from voice_to_notes.providers.local_provider import LocalProvider
 
                 service.register_provider("local", LocalProvider(
-                    base_url=config.get("base_url", "http://localhost:8080"),
+                    base_url=config.get("base_url", "http://localhost:11434/v1"),
-                    model=config.get("model", "local"),
+                    model=config.get("model", "llama3.2"),
                 ))
             elif provider_name == "openai":
                 from voice_to_notes.providers.openai_provider import OpenAIProvider
@@ -286,6 +286,10 @@ def make_ai_chat_handler() -> HandlerFunc:
                     api_key=config.get("api_key"),
                     api_base=config.get("api_base"),
                 ))
+            # Set the configured provider as active
+            print(f"[sidecar] Configured AI provider: {provider_name} with config: {config}", file=sys.stderr, flush=True)
+            if provider_name in ("local", "openai", "anthropic", "litellm"):
+                service.set_active(provider_name)
             return IPCMessage(
                 id=msg.id,
                 type="ai.configured",

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()
 

src-tauri/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "voice-to-notes"
-version = "0.2.27"
+version = "0.2.32"
 description = "Voice to Notes — desktop transcription with speaker identification"
 authors = ["Voice to Notes Contributors"]
 license = "MIT"

src-tauri/src/commands/media.rs

@@ -0,0 +1,104 @@
+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) -> Result<String, String> {
+    let input = PathBuf::from(&file_path);
+    if !input.exists() {
+        return Err(format!("File not found: {}", file_path));
+    }
+
+    // Output to a temp WAV file next to the original or in temp dir
+    let stem = input.file_stem().unwrap_or_default().to_string_lossy();
+    let output = 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",
+            "16000",          // 16kHz (optimal for whisper)
+            "-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())
+}
+
+/// 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/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::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 +74,7 @@ pub fn run() {
             check_sidecar_update,
             log_frontend,
             toggle_devtools,
+            extract_audio,
         ])
         .run(tauri::generate_context!())
         .expect("error while running tauri application");

src-tauri/tauri.conf.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://schema.tauri.app/config/2",
   "productName": "Voice to Notes",
-  "version": "0.2.27",
+  "version": "0.2.32",
   "identifier": "com.voicetonotes.app",
   "build": {
     "beforeDevCommand": "npm run dev",

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

@@ -52,11 +52,7 @@ 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 },
@@ -68,7 +64,15 @@ export async function saveSettings(s: AppSettings): Promise<void> {
     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';
 
@@ -54,6 +54,7 @@
 
   function handleSidecarSetupComplete() {
     sidecarReady = true;
+    configureAIProvider($settings);
     checkSidecarUpdate();
   }
 
@@ -71,6 +72,7 @@
     });
     checkSidecar().then(() => {
       if (sidecarReady) {
+        configureAIProvider($settings);
         checkSidecarUpdate();
       }
     });
@@ -117,9 +119,22 @@
     };
   });
   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'];
@@ -254,6 +269,8 @@
     // Changes persist when user saves the project file.
   }
 
+  const VIDEO_EXTENSIONS = ['mp4', 'mkv', 'avi', 'mov', 'webm'];
+
   async function handleFileImport() {
     const filePath = await open({
       multiple: false,
@@ -265,9 +282,38 @@
     });
     if (!filePath) return;
 
-    // Track the original file path and convert to asset URL for wavesurfer
+    // For video files, extract audio first using ffmpeg
+    const ext = filePath.split('.').pop()?.toLowerCase() ?? '';
+    let audioPath = filePath;
+    if (VIDEO_EXTENSIONS.includes(ext)) {
+      extractingAudio = true;
+      await tick();
+      try {
+        audioPath = await invoke<string>('extract_audio', { filePath });
+      } 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 import video files.\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 from video: ${msg}`);
+        }
+        return;
+      } finally {
+        extractingAudio = false;
+      }
+    }
+
+    // Track the original file path (video or audio) for the sidecar
     audioFilePath = filePath;
-    audioUrl = convertFileSrc(filePath);
+    audioUrl = convertFileSrc(audioPath);
     waveformPlayer?.loadAudio(audioUrl);
 
     // Clear previous results
@@ -276,6 +322,7 @@
 
     // Start pipeline (transcription + diarization)
     isTranscribing = true;
+    transcriptionCancelled = false;
     transcriptionProgress = 0;
     transcriptionStage = 'Starting...';
     transcriptionMessage = 'Initializing pipeline...';
@@ -386,6 +433,9 @@
         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}`,
@@ -573,8 +623,18 @@
     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 from video...</p>
+      </div>
+    </div>
+  {/if}
+
   <SettingsModal
     visible={showSettings}
     onClose={() => showSettings = false}
@@ -781,4 +841,39 @@
   .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>