fix: play Opus TTS audio directly instead of WAV-converting it

The backend sends Opus-encoded audio from OpenAI TTS (tts-1 with
response_format=opus). The frontend was treating it as raw PCM16
and wrapping it in a WAV container, which corrupted the audio into
static. Now plays the Opus data directly as audio/ogg.

frontend/src/hooks/useConversation.ts

@@ -151,28 +151,14 @@ export function useConversation() {
         break;
 
       case 'audio': {
-        // Incoming PCM16 audio from Kira
+        // Incoming Opus audio from TTS (full response, not streamed)
         if (msg.data && audioRef.current) {
-          // Accumulate audio chunks and create a blob
           const binary = atob(msg.data);
           const bytes = new Uint8Array(binary.length);
           for (let i = 0; i < binary.length; i++) {
             bytes[i] = binary.charCodeAt(i);
           }
-          audioBufferRef.current.push(bytes);
-
-          // Convert accumulated PCM16 to WAV blob for playback
-          const allChunks = audioBufferRef.current;
-          const totalLen = allChunks.reduce((s, c) => s + c.length, 0);
-          const combined = new Uint8Array(totalLen);
-          let offset = 0;
-          for (const chunk of allChunks) {
-            combined.set(chunk, offset);
-            offset += chunk.length;
-          }
-
-          const wav = pcm16ToWav(combined);
-          const blob = new Blob([wav], { type: 'audio/wav' });
+          const blob = new Blob([bytes], { type: 'audio/ogg' });
           const url = URL.createObjectURL(blob);
           audioRef.current.src = url;
           audioRef.current.play().catch(() => {});