python/voice_to_notes/ipc/handlers.py

@@ -88,6 +88,57 @@ def make_diarize_handler() -> HandlerFunc:
     return handler
 
 
+def make_diarize_download_handler() -> HandlerFunc:
+    """Create a handler that downloads/validates the diarization model."""
+
+    def handler(msg: IPCMessage) -> IPCMessage:
+        payload = msg.payload
+        hf_token = payload.get("hf_token")
+
+        try:
+            from pyannote.audio import Pipeline
+
+            print("[sidecar] Downloading diarization model...", file=sys.stderr, flush=True)
+            pipeline = Pipeline.from_pretrained(
+                "pyannote/speaker-diarization-3.1",
+                token=hf_token,
+            )
+            print("[sidecar] Diarization model downloaded successfully", file=sys.stderr, flush=True)
+            return IPCMessage(
+                id=msg.id,
+                type="diarize.download.result",
+                payload={"ok": True},
+            )
+        except Exception as e:
+            error_msg = str(e)
+            # Make common errors more user-friendly
+            if "403" in error_msg and "gated" in error_msg.lower():
+                # Extract which model needs access
+                if "segmentation" in error_msg:
+                    error_msg = (
+                        "Access denied for pyannote/segmentation-3.0. "
+                        "Please visit huggingface.co/pyannote/segmentation-3.0 "
+                        "and accept the license agreement."
+                    )
+                elif "speaker-diarization" in error_msg:
+                    error_msg = (
+                        "Access denied for pyannote/speaker-diarization-3.1. "
+                        "Please visit huggingface.co/pyannote/speaker-diarization-3.1 "
+                        "and accept the license agreement."
+                    )
+                else:
+                    error_msg = (
+                        "Access denied. Please accept the license agreements at: "
+                        "huggingface.co/pyannote/speaker-diarization-3.1 and "
+                        "huggingface.co/pyannote/segmentation-3.0"
+                    )
+            elif "401" in error_msg:
+                error_msg = "Invalid token. Please check your HuggingFace token."
+            return error_message(msg.id, "download_error", error_msg)
+
+    return handler
+
+
 def make_pipeline_handler() -> HandlerFunc:
     """Create a full pipeline handler (transcribe + diarize + merge)."""
     from voice_to_notes.services.pipeline import PipelineService, pipeline_result_to_payload

python/voice_to_notes/main.py

@@ -15,6 +15,7 @@ from voice_to_notes.ipc.handlers import (  # noqa: E402
     HandlerRegistry,
     hardware_detect_handler,
     make_ai_chat_handler,
+    make_diarize_download_handler,
     make_diarize_handler,
     make_export_handler,
     make_pipeline_handler,
@@ -32,6 +33,7 @@ def create_registry() -> HandlerRegistry:
     registry.register("transcribe.start", make_transcribe_handler())
     registry.register("hardware.detect", hardware_detect_handler)
     registry.register("diarize.start", make_diarize_handler())
+    registry.register("diarize.download", make_diarize_download_handler())
     registry.register("pipeline.start", make_pipeline_handler())
     registry.register("export.start", make_export_handler())
     registry.register("ai.chat", make_ai_chat_handler())

src-tauri/src/commands/transcribe.rs

@@ -40,6 +40,35 @@ pub fn transcribe_file(
     Ok(response.payload)
 }
 
+/// Download and validate the diarization model via the Python sidecar.
+#[tauri::command]
+pub fn download_diarize_model(
+    hf_token: String,
+) -> Result<Value, String> {
+    let manager = sidecar();
+    manager.ensure_running()?;
+
+    let request_id = uuid::Uuid::new_v4().to_string();
+    let msg = IPCMessage::new(
+        &request_id,
+        "diarize.download",
+        json!({
+            "hf_token": hf_token,
+        }),
+    );
+
+    let response = manager.send_and_receive(&msg)?;
+
+    if response.msg_type == "error" {
+        return Ok(json!({
+            "ok": false,
+            "error": response.payload.get("message").and_then(|v| v.as_str()).unwrap_or("unknown"),
+        }));
+    }
+
+    Ok(json!({ "ok": true }))
+}
+
 /// Run the full transcription + diarization pipeline via the Python sidecar.
 #[tauri::command]
 pub fn run_pipeline(

src-tauri/src/lib.rs

@@ -12,7 +12,7 @@ use commands::export::export_transcript;
 use commands::project::{create_project, get_project, list_projects};
 use commands::settings::{load_settings, save_settings};
 use commands::system::{get_data_dir, llama_list_models, llama_start, llama_status, llama_stop};
-use commands::transcribe::{run_pipeline, transcribe_file};
+use commands::transcribe::{download_diarize_model, run_pipeline, transcribe_file};
 use state::AppState;
 
 #[cfg_attr(mobile, tauri::mobile_entry_point)]
@@ -36,6 +36,7 @@ pub fn run() {
             list_projects,
             transcribe_file,
             run_pipeline,
+            download_diarize_model,
             export_transcript,
             ai_chat,
             ai_list_providers,

src/lib/components/SettingsModal.svelte

@@ -1,4 +1,6 @@
 <script lang="ts">
+  import { invoke } from '@tauri-apps/api/core';
+  import { openUrl } from '@tauri-apps/plugin-opener';
   import { settings, saveSettings, type AppSettings } from '$lib/stores/settings';
 
   interface Props {
@@ -10,6 +12,32 @@
 
   let localSettings = $state<AppSettings>({ ...$settings });
   let activeTab = $state<'transcription' | 'speakers' | 'ai' | 'local'>('transcription');
+  let modelStatus = $state<'idle' | 'downloading' | 'success' | 'error'>('idle');
+  let modelError = $state('');
+
+  async function testAndDownloadModel() {
+    if (!localSettings.hf_token) {
+      modelStatus = 'error';
+      modelError = 'Please enter a HuggingFace token first.';
+      return;
+    }
+    modelStatus = 'downloading';
+    modelError = '';
+    try {
+      const result = await invoke<{ ok: boolean; error?: string }>('download_diarize_model', {
+        hfToken: localSettings.hf_token,
+      });
+      if (result.ok) {
+        modelStatus = 'success';
+      } else {
+        modelStatus = 'error';
+        modelError = result.error || 'Unknown error';
+      }
+    } catch (err) {
+      modelStatus = 'error';
+      modelError = String(err);
+    }
+  }
 
   // Sync when settings store changes
   $effect(() => {
@@ -86,18 +114,41 @@
             <input id="hf-token" type="password" bind:value={localSettings.hf_token} placeholder="hf_..." />
           </div>
           <div class="info-box">
-            <p class="info-title">Why is this needed?</p>
-            <p>Speaker detection uses the <strong>pyannote.audio</strong> model, which is hosted on HuggingFace and requires accepting a license agreement.</p>
-            <p class="info-title">How to get a token:</p>
+            <p class="info-title">Setup (one-time)</p>
+            <p>Speaker detection uses <strong>pyannote.audio</strong> models hosted on HuggingFace. You must accept the license for each model:</p>
             <ol>
-              <li>Create a free account at <strong>huggingface.co</strong></li>
-              <li>Go to <strong>huggingface.co/pyannote/speaker-diarization-3.1</strong> and accept the license</li>
-              <li>Go to <strong>huggingface.co/settings/tokens</strong> and create a token with <em>read</em> access</li>
-              <li>Paste the token above and click Save</li>
+              <li>Create a free account at <!-- svelte-ignore a11y_no_static_element_interactions --><a class="ext-link" onclick={() => openUrl('https://huggingface.co/join')}>huggingface.co</a></li>
+              <li>Accept the license on <strong>each</strong> of these pages:
+                <ul>
+                  <!-- svelte-ignore a11y_no_static_element_interactions -->
+                  <li><a class="ext-link" onclick={() => openUrl('https://huggingface.co/pyannote/speaker-diarization-3.1')}>pyannote/speaker-diarization-3.1</a></li>
+                  <!-- svelte-ignore a11y_no_static_element_interactions -->
+                  <li><a class="ext-link" onclick={() => openUrl('https://huggingface.co/pyannote/segmentation-3.0')}>pyannote/segmentation-3.0</a></li>
+                </ul>
+              </li>
+              <!-- svelte-ignore a11y_no_static_element_interactions -->
+              <li>Create a token at <a class="ext-link" onclick={() => openUrl('https://huggingface.co/settings/tokens')}>huggingface.co/settings/tokens</a> (read access)</li>
+              <li>Paste the token above and click <strong>Test & Download</strong></li>
             </ol>
-            <p>The model will be downloaded automatically on first use (~100 MB).</p>
           </div>
-          <div class="field checkbox">
+          <button
+            class="btn-download"
+            onclick={testAndDownloadModel}
+            disabled={modelStatus === 'downloading'}
+          >
+            {#if modelStatus === 'downloading'}
+              Downloading model...
+            {:else}
+              Test & Download Model
+            {/if}
+          </button>
+          {#if modelStatus === 'success'}
+            <p class="status-success">Model downloaded successfully. Speaker detection is ready.</p>
+          {/if}
+          {#if modelStatus === 'error'}
+            <p class="status-error">{modelError}</p>
+          {/if}
+          <div class="field checkbox" style="margin-top: 1rem;">
             <label>
               <input type="checkbox" bind:checked={localSettings.skip_diarization} />
               Skip speaker detection (faster, no speaker labels)
@@ -303,6 +354,48 @@
   .info-box strong {
     color: #e0e0e0;
   }
+  .ext-link {
+    color: #e94560;
+    cursor: pointer;
+    text-decoration: underline;
+  }
+  .ext-link:hover {
+    color: #ff6b81;
+  }
+  .info-box ul {
+    margin: 0.25rem 0;
+    padding-left: 1.25rem;
+  }
+  .btn-download {
+    background: #0f3460;
+    border: 1px solid #4a5568;
+    color: #e0e0e0;
+    padding: 0.5rem 1rem;
+    border-radius: 6px;
+    cursor: pointer;
+    font-size: 0.85rem;
+    width: 100%;
+    margin-bottom: 0.5rem;
+  }
+  .btn-download:hover:not(:disabled) {
+    background: #1a4a7a;
+    border-color: #e94560;
+  }
+  .btn-download:disabled {
+    opacity: 0.6;
+    cursor: not-allowed;
+  }
+  .status-success {
+    color: #4ecdc4;
+    font-size: 0.8rem;
+    margin: 0.25rem 0;
+  }
+  .status-error {
+    color: #e94560;
+    font-size: 0.8rem;
+    margin: 0.25rem 0;
+    word-break: break-word;
+  }
   .modal-footer {
     display: flex;
     justify-content: flex-end;