feat(desktop): add Pocket voice settings

desktop/playwright.config.ts

@@ -48,6 +48,7 @@ export default defineConfig({
         "**/activity-scope-label-screenshots.spec.ts",
         "**/welcome-agent-modal-screenshots.spec.ts",
         "**/local-archive-screenshots.spec.ts",
+        "**/voice-settings.spec.ts",
         "**/agent-readiness-screenshots.spec.ts",
         "**/agent-error-state-screenshots.spec.ts",
         "**/edit-agent.spec.ts",

desktop/src-tauri/resources/pocket-voices/NOTICE.md

@@ -0,0 +1,35 @@
+# Pocket TTS English VCTK presets
+
+Buzz exposes Kyutai's twelve official English VCTK Pocket presets. The WAV
+bytes are unchanged from `kyutai/tts-voices` revision
+`323332d33f997de8394f24a193e1a76df720e01a`; only local filenames differ.
+
+| Voice | Upstream asset | SHA-256 |
+| --- | --- | --- |
+| Anna | `vctk/p228_023_enhanced.wav` | `0a6de25cf12bf1540beb85979f306a92be81fecc051c547c5395e7e5237a3856` |
+| Vera | `vctk/p229_023_enhanced.wav` | `309cf91a895830f15842b398f69a4962cb1f7e0bfab10e25dd27838e826c204b` |
+| Fantine | `vctk/p244_023_enhanced.wav` | `5f07d4e2a3f20a15572aae885156b43ef3fc12ef3812996fd135680d9956448b` |
+| Charles | `vctk/p254_023_enhanced.wav` | `6b681a429198f16e378d53bccb08d06939da7b00144a7696111d4f8f76be7756` |
+| Paul | `vctk/p259_023_enhanced.wav` | `7aba504fe0b3b16478b69eb27ce6007e3cb42b0c1915b5f1c6a6024ae37d679b` |
+| Eponine | `vctk/p262_023_enhanced.wav` | `a13c27fb47627b05223691a0ef2974358a18c886e6c2f9d2762ff1d02c20926b` |
+| Azelma | `vctk/p303_023_enhanced.wav` | `60e3d26cdf2efdec5df712152c839928f4d5522821e6554ae11fd96c57ab1026` |
+| George | `vctk/p315_023_enhanced.wav` | `29a41f93bf5236e5b21501091d7774c255d5f3d4e62fa4f9fdf0a92a793c84ae` |
+| Mary | `vctk/p333_023_enhanced.wav` | `a35b0468382218e9f37a9a7494d1e4b74deaf18d7ced22265b4e325bb55c183f` |
+| Jane | `vctk/p339_023_enhanced.wav` | `2f12e7f155eb3118f55425394f1b049e5b1b67bdc9b3932c8ba4521420aeb84a` |
+| Michael | `vctk/p360_023_enhanced.wav` | `b6743e9195e5e3fd34fe9d1633ae93f7ffab787b249e45f6467d7d6f7a6ee6ad` |
+| Eve | `vctk/p361_023_enhanced.wav` | `396e7cbd066b0f3fb6d67fa26e7904076958239d736d4390f15b5fe88feb14cd` |
+
+Mary is already installed as the Pocket model's `reference_sample.wav`, so it
+is not duplicated in this resource directory.
+
+Source repository:
+https://huggingface.co/kyutai/tts-voices/tree/323332d33f997de8394f24a193e1a76df720e01a/vctk
+
+The original recordings are from the Voice Cloning Toolkit (VCTK) corpus,
+licensed CC BY 4.0:
+https://datashare.ed.ac.uk/handle/10283/3443
+
+The recordings were enhanced by ai-coustics:
+https://ai-coustics.com/
+
+Neither Kyutai, the VCTK speakers, nor ai-coustics endorses Buzz.

desktop/src-tauri/src/app_state.rs

@@ -48,15 +48,13 @@ pub struct AppState {
     pub channel_templates_store_lock: Mutex<()>,
     pub managed_agent_processes: Mutex<HashMap<ManagedAgentRuntimeKey, ManagedAgentPairRuntime>>,
     pub huddle_state: Mutex<HuddleState>,
+    pub huddle_audio: crate::huddle::tts_settings::HuddleAudioSettingsState,
     /// Tauri app handle — stored after setup so huddle commands can emit
     /// `huddle-state-changed` events without needing the handle threaded
     /// through every call site.
     ///
     /// Set once during `setup()` in `lib.rs`; never cleared.
     pub app_handle: Mutex<Option<AppHandle>>,
-    /// Selected audio output device name. `None` = system default.
-    /// Used by `connect_audio_relay` and TTS pipeline when opening sinks.
-    pub audio_output_device: Mutex<Option<String>>,
     /// Port of the localhost media streaming proxy (set during setup).
     pub media_proxy_port: AtomicU16,
     /// Set when identity resolution detected a "keyring-locked" state: the
@@ -213,8 +211,8 @@ pub fn build_app_state() -> AppState {
         managed_agent_processes: Mutex::new(HashMap::new()),
         session_config_cache: Mutex::new(HashMap::new()),
         huddle_state: Mutex::new(HuddleState::default()),
+        huddle_audio: Default::default(),
         app_handle: Mutex::new(None),
-        audio_output_device: Mutex::new(None),
         media_proxy_port: AtomicU16::new(0),
         prevent_sleep: Arc::new(Mutex::new(
             crate::prevent_sleep::PreventSleepState::default(),

desktop/src-tauri/src/huddle/agent_tts_routing.rs

@@ -0,0 +1,56 @@
+use super::HuddlePhase;
+
+#[derive(Debug, PartialEq, Eq)]
+pub(super) enum AgentTtsRuntimeGate {
+    Disabled,
+    Inactive,
+    NeedsPipeline,
+    Ready,
+}
+
+pub(super) fn classify_agent_tts_runtime(
+    enabled: bool,
+    phase: &HuddlePhase,
+    has_pipeline: bool,
+) -> AgentTtsRuntimeGate {
+    if !enabled {
+        AgentTtsRuntimeGate::Disabled
+    } else if !matches!(phase, HuddlePhase::Connected | HuddlePhase::Active) {
+        AgentTtsRuntimeGate::Inactive
+    } else if has_pipeline {
+        AgentTtsRuntimeGate::Ready
+    } else {
+        AgentTtsRuntimeGate::NeedsPipeline
+    }
+}
+
+/// Maximum text length accepted for TTS synthesis.
+/// ~2000 chars is 1–2 minutes of speech. Longer messages are truncated.
+pub(super) const MAX_TTS_TEXT_LEN: usize = 2000;
+
+pub(super) fn normalize_agent_tts_text(text: String) -> String {
+    if text.chars().count() > MAX_TTS_TEXT_LEN {
+        let mut truncated: String = text.chars().take(MAX_TTS_TEXT_LEN).collect();
+        truncated.push_str("... message truncated.");
+        truncated
+    } else {
+        text
+    }
+}
+
+pub(super) async fn enqueue_agent_tts_text<F>(
+    route_id: u64,
+    text: String,
+    enqueue: F,
+) -> Result<(), String>
+where
+    F: FnOnce(u64, String) -> Result<(), String> + Send + 'static,
+{
+    tokio::task::spawn_blocking(move || enqueue(route_id, text))
+        .await
+        .map_err(|error| format!("TTS enqueue task failed: {error}"))?
+}
+
+#[cfg(test)]
+#[path = "agent_tts_routing_tests.rs"]
+mod tests;

desktop/src-tauri/src/huddle/agent_tts_routing_tests.rs

@@ -0,0 +1,57 @@
+use super::{
+    classify_agent_tts_runtime, enqueue_agent_tts_text, normalize_agent_tts_text,
+    AgentTtsRuntimeGate, MAX_TTS_TEXT_LEN,
+};
+use crate::huddle::HuddlePhase;
+
+#[tokio::test]
+async fn assistant_plain_text_routes_unchanged_into_voice_pipeline_boundary() {
+    let (sender, receiver) = std::sync::mpsc::channel();
+    let text = "A newly submitted assistant reply.".to_string();
+    let route_id = 42;
+
+    enqueue_agent_tts_text(route_id, text.clone(), move |route_id, queued| {
+        sender
+            .send((route_id, queued))
+            .map_err(|error| error.to_string())
+    })
+    .await
+    .expect("route assistant text");
+
+    assert_eq!(
+        receiver.recv().expect("queued text"),
+        (route_id, text),
+        "route correlation must survive the native queue boundary"
+    );
+}
+
+#[test]
+fn disabled_is_the_only_intentional_runtime_no_op() {
+    assert_eq!(
+        classify_agent_tts_runtime(false, &HuddlePhase::Connected, false),
+        AgentTtsRuntimeGate::Disabled
+    );
+    assert_eq!(
+        classify_agent_tts_runtime(true, &HuddlePhase::Idle, false),
+        AgentTtsRuntimeGate::Inactive
+    );
+    assert_eq!(
+        classify_agent_tts_runtime(true, &HuddlePhase::Connected, false),
+        AgentTtsRuntimeGate::NeedsPipeline
+    );
+    assert_eq!(
+        classify_agent_tts_runtime(true, &HuddlePhase::Connected, true),
+        AgentTtsRuntimeGate::Ready
+    );
+}
+
+#[test]
+fn assistant_text_truncation_is_unicode_safe_before_voice_routing() {
+    let input = "🦀".repeat(MAX_TTS_TEXT_LEN + 1);
+    let output = normalize_agent_tts_text(input);
+    assert_eq!(
+        output.chars().count(),
+        MAX_TTS_TEXT_LEN + "... message truncated.".chars().count()
+    );
+    assert!(output.ends_with("... message truncated."));
+}

desktop/src-tauri/src/huddle/audio_output.rs

@@ -39,7 +39,8 @@ fn list_audio_output_devices_blocking() -> Result<Vec<AudioOutputDevice>, String
 #[tauri::command]
 pub fn set_audio_output_device(name: String, state: State<'_, AppState>) -> Result<(), String> {
     let mut guard = state
-        .audio_output_device
+        .huddle_audio
+        .output_device
         .lock()
         .map_err(|e| e.to_string())?;
     *guard = if name.is_empty() { None } else { Some(name) };
@@ -50,7 +51,8 @@ pub fn set_audio_output_device(name: String, state: State<'_, AppState>) -> Resu
 #[tauri::command]
 pub fn get_audio_output_device(state: State<'_, AppState>) -> Result<String, String> {
     let guard = state
-        .audio_output_device
+        .huddle_audio
+        .output_device
         .lock()
         .map_err(|e| e.to_string())?;
     Ok(guard.clone().unwrap_or_default())