Skip to main content

How to play audio from decoded base64 string with ElevenLabs Streaming Websocket Typescript

I am attempting to use the ElevenLabs API and Websockets to stream audio to the browser. response.audio does return a generated partial MP3 audio chunk encoded as a base64 string, but I am stuck on trying to properly decode and play it. This is my current attempt:

Main notes:

  • The API does return a response of base64 string successfully
  • I keep receiving the error on Chrome: Uncaught (in promise) DOMException: Failed to load because no supported source was found.
  • My blob url returns a 404 error

Here is my code:

"use client";


import React, { useRef, useState } from 'react';

const StreamingAudioTest: React.FC = () => {

  const [isPlaying, setIsPlaying] = useState(false);
  const audioRef = useRef<HTMLAudioElement | null>(null);

  const handlePlayButtonClick = () => {

    const voiceId = "<voice-id>";
    const model = 'eleven_monolingual_v1';
    const wsUrl = `wss://api.elevenlabs.io/v1/text-to-speech/${voiceId}/stream-input?model_id=${model}`;
    const socket = new WebSocket(wsUrl);

    socket.onopen = function (event) {
      const bosMessage = {
        "text": " ",
        "voice_settings": {
          "stability": 0.5,
          "similarity_boost": true
        },
        "xi_api_key": "<api-key>", // replace with your API key
      };

      socket.send(JSON.stringify(bosMessage));

      const textMessage = {
        "text": "Hello ",
        "try_trigger_generation": true,
      };

      socket.send(JSON.stringify(textMessage));

      const eosMessage = {
        "text": ""
      };

      socket.send(JSON.stringify(eosMessage));
    };

    socket.onmessage = async function (event) {
      const response = await JSON.parse(event.data);

   
      if (response.audio) {
        
        const audioChunk = atob(response.audio); // decode base64

  
      
        console.log("Recieved audio chunk")

        if (audioRef.current) {
            const blob = new Blob([audioChunk], { type: 'audio/mp3' }); 
            audioRef.current.src = URL.createObjectURL(blob);
            audioRef.current.play();
          }
        
      }

      if (response.isFinal) {
        // Handle generation completion
      }

      if (response.normalizedAlignment) {
        // Handle alignment info if needed
      }
    };

    socket.onerror = function (error) {
      console.error(`WebSocket Error: ${error}`);
    };

    socket.onclose = function (event) {
      if (event.wasClean) {
        console.info(`Connection closed cleanly, code=${event.code}, reason=${event.reason}`);
      } else {
        console.warn('Connection died');
      }
    };

    // Cleanup the WebSocket when the component unmounts
    return () => {
      socket.close();
    };
  };


  return (
    <div className='text-red-500'>
      <h1>Text-to-Speech Audio Player</h1>
      <button onClick={handlePlayButtonClick} disabled={isPlaying}>
        {isPlaying ? 'Playing...' : 'Play Audio'}
      </button>
      {/* <audio ref={audioRef} controls /> */}

      <audio ref={audioRef} autoPlay controls />
    </div>
  );
};




export default StreamingAudioTest;

Via Active questions tagged javascript - Stack Overflow https://ift.tt/t9AZyWC

Comments

Popular posts from this blog

ValueError: X has 10 features, but LinearRegression is expecting 1 features as input

So, I am trying to predict the model but its throwing error like it has 10 features but it expacts only 1. So I am confused can anyone help me with it? more importantly its not working for me when my friend runs it. It works perfectly fine dose anyone know the reason about it? cv = KFold(n_splits = 10) all_loss = [] for i in range(9): # 1st for loop over polynomial orders poly_order = i X_train = make_polynomial(x, poly_order) loss_at_order = [] # initiate a set to collect loss for CV for train_index, test_index in cv.split(X_train): print('TRAIN:', train_index, 'TEST:', test_index) X_train_cv, X_test_cv = X_train[train_index], X_test[test_index] t_train_cv, t_test_cv = t[train_index], t[test_index] reg.fit(X_train_cv, t_train_cv) loss_at_order.append(np.mean((t_test_cv - reg.predict(X_test_cv))**2)) # collect loss at fold all_loss.append(np.mean(loss_at_order)) # collect loss at order plt.plot(np.log(al...

Sorting large arrays of big numeric stings

I was solving bigSorting() problem from hackerrank: Consider an array of numeric strings where each string is a positive number with anywhere from to digits. Sort the array's elements in non-decreasing, or ascending order of their integer values and return the sorted array. I know it works as follows: def bigSorting(unsorted): return sorted(unsorted, key=int) But I didnt guess this approach earlier. Initially I tried below: def bigSorting(unsorted): int_unsorted = [int(i) for i in unsorted] int_sorted = sorted(int_unsorted) return [str(i) for i in int_sorted] However, for some of the test cases, it was showing time limit exceeded. Why is it so? PS: I dont know exactly what those test cases were as hacker rank does not reveal all test cases. source https://stackoverflow.com/questions/73007397/sorting-large-arrays-of-big-numeric-stings

How to load Javascript with imported modules?

I am trying to import modules from tensorflowjs, and below is my code. test.html <!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8"> <title>Document</title </head> <body> <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@2.0.0/dist/tf.min.js"></script> <script type="module" src="./test.js"></script> </body> </html> test.js import * as tf from "./node_modules/@tensorflow/tfjs"; import {loadGraphModel} from "./node_modules/@tensorflow/tfjs-converter"; const MODEL_URL = './model.json'; const model = await loadGraphModel(MODEL_URL); const cat = document.getElementById('cat'); model.execute(tf.browser.fromPixels(cat)); Besides, I run the server using python -m http.server in my command prompt(Windows 10), and this is the error prompt in the console log of my browser: Failed to loa...