fix: handle blob responses, construct wav header in example

examples/node-speak-live/index.js

@@ -1,14 +1,38 @@
 const fs = require("fs");
 const { createClient, LiveTTSEvents } = require("../../dist/main/index");
 
+// Add a wav audio container header to the file if you want to play the audio
+// using the AudioContext or media player like VLC, Media Player, or Apple Music
+// Without this header in the Chrome browser case, the audio will not play.
+// prettier-ignore
+const wavHeader = [
+  0x52, 0x49, 0x46, 0x46, // "RIFF"
+  0x00, 0x00, 0x00, 0x00, // Placeholder for file size
+  0x57, 0x41, 0x56, 0x45, // "WAVE"
+  0x66, 0x6D, 0x74, 0x20, // "fmt "
+  0x10, 0x00, 0x00, 0x00, // Chunk size (16)
+  0x01, 0x00,             // Audio format (1 for PCM)
+  0x01, 0x00,             // Number of channels (1)
+  0x80, 0xBB, 0x00, 0x00, // Sample rate (48000)
+  0x00, 0xEE, 0x02, 0x00, // Byte rate (48000 * 2)
+  0x02, 0x00,             // Block align (2)
+  0x10, 0x00,             // Bits per sample (16)
+  0x64, 0x61, 0x74, 0x61, // "data"
+  0x00, 0x00, 0x00, 0x00  // Placeholder for data size
+];
+
 const live = async () => {
   const text = "Hello, how can I help you today?";
 
   const deepgram = createClient(process.env.DEEPGRAM_API_KEY);
 
-  const dgConnection = deepgram.speak.live({ model: "aura-asteria-en" });
+  const dgConnection = deepgram.speak.live({
+    model: "aura-asteria-en",
+    encoding: "linear16",
+    sample_rate: 48000,
+  });
 
-  let audioBuffer = Buffer.alloc(0);
+  let audioBuffer = Buffer.from(wavHeader);
 
   dgConnection.on(LiveTTSEvents.Open, () => {
     console.log("Connection opened");
@@ -47,14 +71,14 @@ const live = async () => {
 
   const writeFile = () => {
     if (audioBuffer.length > 0) {
-      fs.writeFile("output.mp3", audioBuffer, (err) => {
+      fs.writeFile("output.wav", audioBuffer, (err) => {
         if (err) {
           console.error("Error writing audio file:", err);
         } else {
-          console.log("Audio file saved as output.mp3");
+          console.log("Audio file saved as output.wav");
         }
       });
-      audioBuffer = Buffer.alloc(0); // Reset buffer after writing
+      audioBuffer = Buffer.from(wavHeader); // Reset buffer after writing
     }
   };
 };

src/packages/SpeakLiveClient.ts

@@ -81,7 +81,7 @@ export class SpeakLiveClient extends AbstractLiveClient {
    * Handles binary messages received from the WebSocket connection.
    * @param data - The binary data.
    */
-  protected handleBinaryMessage(data: ArrayBuffer): void {
+  protected handleBinaryMessage(data: Buffer): void {
     this.emit(LiveTTSEvents.Audio, data);
   }
 
@@ -148,10 +148,14 @@ export class SpeakLiveClient extends AbstractLiveClient {
           error,
         });
       }
+    } else if (event.data instanceof Blob) {
+      event.data.arrayBuffer().then((buffer) => {
+        this.handleBinaryMessage(Buffer.from(buffer));
+      });
     } else if (event.data instanceof ArrayBuffer) {
-      this.handleBinaryMessage(event.data);
+      this.handleBinaryMessage(Buffer.from(event.data));
     } else if (Buffer.isBuffer(event.data)) {
-      this.handleBinaryMessage(event.data.buffer);
+      this.handleBinaryMessage(event.data);
     } else {
       console.log("Received unknown data type", event.data);
       this.emit(LiveTTSEvents.Error, {