TextToSpeech.cs

using System;
using System.Collections;
using System.Collections.Generic;
using UnityEngine;

namespace Goldsaucer.Askutron.TTS
{
    public class TextToSpeech
    {
        private const string ServerUrl = "https://example.com";
        
        public readonly string Text;
        public readonly string Language;
        public readonly string AudioUri;

        public AudioClip AudioClip { get; private set; }
        
        public TextToSpeech(string text, string language, string audioUri = null)
        {
            Text = text;
            Language = language;
            AudioUri = audioUri;
        }

        /// <summary>
        /// Generate HTTP headers required to fetch audio from the server.
        /// </summary>
        /// <param name="phrase">text for which to download the audio</param>
        /// <returns>A dictionary with the HTTP headers</returns>
        private static Dictionary<string, string> GenerateRequestHeaders(TextToSpeech phrase)
        {
            var headers = new Dictionary<string, string>();

            // [...] add required authentication headers etc.

            return headers;
        }

        /// <summary>
        /// Load the question's audio
        /// </summary>
        public IEnumerator Load()
        {
            var uri = AudioUri ?? $"/audios/playback?ssmd={Uri.EscapeUriString(Text)}&language={Language}";
            var headers = GenerateRequestHeaders(this);
            var request = new WWW(ServerUrl + uri, null, headers);

            yield return request;

            AudioClip = request.GetAudioClipCompressed(false, AudioType.OGGVORBIS);
        }

        /// <summary>
        /// Read the question out aloud
        /// </summary>
        public IEnumerator Play()
        {
            AudioSource.PlayClipAtPoint(AudioClip, Vector3.zero);

            yield return new WaitForSeconds(AudioClip.length);
        }
    }
}