Project folders, always-extract audio, re-link support

Projects now save as folders containing .vtn + audio.wav: My Transcript/ My Transcript.vtn audio.wav Audio handling: - Always extract to 22kHz mono WAV on import (all formats, not just video) - Prevents WebAudio crash from decoding large MP3/FLAC/OGG to PCM in memory - WAV saved alongside .vtn on project save (moved from temp) - Sidecar still uses original file (does its own conversion) Project format v2: - source_file: original import path (for re-extraction) - audio_wav: relative path to extracted WAV (portable) Re-link on open: - If audio.wav exists → load directly - If missing but source exists → re-extract automatically - If both missing → dialog to locate file via file picker - V1 project migration: extracts WAV on first open New Rust commands: check_file_exists, copy_file, create_dir extract_audio: now accepts optional output_path, uses 22kHz sample rate Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-23 08:47:06 -07:00
parent 82bfcfb793
commit 2e9f2519b1
3 changed files with 212 additions and 48 deletions
--- a/src-tauri/src/commands/media.rs
+++ b/src-tauri/src/commands/media.rs
@@ -7,15 +7,18 @@ 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> {
+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));
    }

-    // Output to a temp WAV file next to the original or in temp dir
+    // 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 = std::env::temp_dir().join(format!("{stem}_audio.wav"));
+    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: {} -> {}",
@@ -35,7 +38,7 @@ pub fn extract_audio(file_path: String) -> Result<String, String> {
            "-acodec",
            "pcm_s16le",      // WAV PCM 16-bit
            "-ar",
-            "16000",          // 16kHz (optimal for whisper)
+            "22050",          // 22kHz mono for better playback quality
            "-ac",
            "1",              // Mono
        ])
@@ -63,6 +66,23 @@ pub fn extract_audio(file_path: String) -> Result<String, String> {
    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)
--- a/src-tauri/src/lib.rs
+++ b/src-tauri/src/lib.rs
@@ -9,7 +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::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,
@@ -75,6 +75,9 @@ pub fn run() {
            log_frontend,
            toggle_devtools,
            extract_audio,
+            check_file_exists,
+            copy_file,
+            create_dir,
        ])
        .run(tauri::generate_context!())
        .expect("error while running tauri application");
--- a/src/routes/+page.svelte
+++ b/src/routes/+page.svelte
@@ -32,6 +32,7 @@
  let currentProjectPath = $state<string | null>(null);
  let currentProjectName = $state('');
  let audioFilePath = $state('');
+  let audioWavPath = $state('');

  async function checkSidecar() {
    try {
@@ -147,10 +148,19 @@
    });
    if (!outputPath) return;

+    // Derive folder path and file name from the chosen .vtn path
+    const vtnFileName = outputPath.split(/[\\/]/).pop() || `${defaultName}.vtn`;
+    const projectName = vtnFileName.replace(/\.vtn$/i, '');
+    const parentDir = outputPath.replace(/[\\/][^\\/]+$/, '');
+    const folderPath = `${parentDir}/${projectName}`;
+    const vtnInsideFolder = `${folderPath}/${vtnFileName}`;
+    const wavInsideFolder = `${folderPath}/audio.wav`;
+
    const projectData = {
-      version: 1,
-      name: outputPath.split(/[\\/]/).pop()?.replace('.vtn', '') || defaultName,
-      audio_file: audioFilePath,
+      version: 2,
+      name: projectName,
+      source_file: audioFilePath,
+      audio_wav: 'audio.wav',
      created_at: new Date().toISOString(),
      segments: $segments.map(seg => {
        const speaker = $speakers.find(s => s.id === seg.speaker_id);
@@ -176,9 +186,19 @@
    };

    try {
-      await invoke('save_project_file', { path: outputPath, project: projectData });
-      currentProjectPath = outputPath;
-      currentProjectName = projectData.name;
+      // Create the project folder
+      await invoke('create_dir', { path: folderPath });
+
+      // Copy the extracted WAV into the project folder
+      if (audioWavPath) {
+        await invoke('copy_file', { src: audioWavPath, dst: wavInsideFolder });
+      }
+
+      // Save the .vtn file inside the folder
+      await invoke('save_project_file', { path: vtnInsideFolder, project: projectData });
+
+      currentProjectPath = vtnInsideFolder;
+      currentProjectName = projectName;
    } catch (err) {
      console.error('Failed to save project:', err);
      alert(`Failed to save: ${err}`);
@@ -194,9 +214,11 @@

    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;
@@ -246,10 +268,134 @@
      }));
      segments.set(newSegments);

-      // Load audio
-      audioFilePath = project.audio_file;
-      audioUrl = convertFileSrc(project.audio_file);
-      waveformPlayer?.loadAudio(audioUrl);
+      // Determine the directory the .vtn file is in
+      const vtnDir = (filePath as string).replace(/[\\/][^\\/]+$/, '');
+      const version = project.version ?? 1;
+
+      // Resolve audio for wavesurfer playback
+      if (version >= 2) {
+        // Version 2: audio_wav is relative to the .vtn directory, source_file is the original import path
+        audioFilePath = project.source_file || '';
+        const wavRelative = project.audio_wav || 'audio.wav';
+        const resolvedWav = `${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;
@@ -269,8 +415,6 @@
    // 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,
@@ -282,38 +426,35 @@
    });
    if (!filePath) return;

-    // 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;
+    // 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 (video or audio) for the sidecar
+    // Track the original file path for the sidecar (it does its own conversion)
    audioFilePath = filePath;
-    audioUrl = convertFileSrc(audioPath);
+    audioUrl = convertFileSrc(audioWavPath);
    waveformPlayer?.loadAudio(audioUrl);

    // Clear previous results
@@ -630,7 +771,7 @@
    <div class="extraction-overlay">
      <div class="extraction-card">
        <div class="extraction-spinner"></div>
-        <p>Extracting audio from video...</p>
+        <p>Extracting audio...</p>
      </div>
    </div>
  {/if}