feat(proxy-engine): integrate Kokoro TTS generation into proxy-engine and simplify TypeScript prompt handling to use cached WAV files

rust/crates/proxy-engine/src/main.rs

@@ -21,6 +21,7 @@ mod rtp;
 mod sip_leg;
 mod sip_transport;
 mod tool_leg;
+mod tts;
 mod voicemail;
 mod webrtc_engine;
 
@@ -93,6 +94,9 @@ async fn main() {
     // WebRTC engine — separate lock to avoid deadlock with SIP handlers.
     let webrtc = Arc::new(Mutex::new(WebRtcEngine::new(out_tx.clone())));
 
+    // TTS engine — separate lock, lazy-loads model on first use.
+    let tts_engine = Arc::new(Mutex::new(tts::TtsEngine::new()));
+
     // Read commands from stdin.
     let stdin = tokio::io::stdin();
     let reader = BufReader::new(stdin);
@@ -113,11 +117,12 @@ async fn main() {
 
         let engine = engine.clone();
         let webrtc = webrtc.clone();
+        let tts_engine = tts_engine.clone();
         let out_tx = out_tx.clone();
 
         // Handle commands — some are async, so we spawn.
         tokio::spawn(async move {
-            handle_command(engine, webrtc, &out_tx, cmd).await;
+            handle_command(engine, webrtc, tts_engine, &out_tx, cmd).await;
         });
     }
 }
@@ -125,6 +130,7 @@ async fn main() {
 async fn handle_command(
     engine: Arc<Mutex<ProxyEngine>>,
     webrtc: Arc<Mutex<WebRtcEngine>>,
+    tts_engine: Arc<Mutex<tts::TtsEngine>>,
     out_tx: &OutTx,
     cmd: Command,
 ) {
@@ -150,6 +156,8 @@ async fn handle_command(
         "add_tool_leg" => handle_add_tool_leg(engine, out_tx, &cmd).await,
         "remove_tool_leg" => handle_remove_tool_leg(engine, out_tx, &cmd).await,
         "set_leg_metadata" => handle_set_leg_metadata(engine, out_tx, &cmd).await,
+        // TTS command — lock tts_engine only (no SIP/WebRTC contention).
+        "generate_tts" => handle_generate_tts(tts_engine, out_tx, &cmd).await,
         _ => respond_err(out_tx, &cmd.id, &format!("unknown command: {}", cmd.method)),
     }
 }
@@ -1218,3 +1226,16 @@ async fn handle_set_leg_metadata(
     leg.metadata.insert(key, value);
     respond_ok(out_tx, &cmd.id, serde_json::json!({}));
 }
+
+/// Handle `generate_tts` — synthesize text to a WAV file using Kokoro TTS.
+async fn handle_generate_tts(
+    tts_engine: Arc<Mutex<tts::TtsEngine>>,
+    out_tx: &OutTx,
+    cmd: &Command,
+) {
+    let mut tts = tts_engine.lock().await;
+    match tts.generate(&cmd.params).await {
+        Ok(result) => respond_ok(out_tx, &cmd.id, result),
+        Err(e) => respond_err(out_tx, &cmd.id, &e),
+    }
+}