File size: 3,781 Bytes
f56a29b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
/**
 * Browser Native TTS (Text-to-Speech) Hook
 * Uses Web Speech API for client-side text-to-speech
 * Completely free, no API key required
 */

import { useState, useCallback, useRef, useEffect } from 'react';

// Note: Window.SpeechSynthesis declaration is already in the global scope

export interface UseBrowserTTSOptions {
  onStart?: () => void;
  onEnd?: () => void;
  onError?: (error: string) => void;
  rate?: number; // 0.1 to 10
  pitch?: number; // 0 to 2
  volume?: number; // 0 to 1
  lang?: string; // e.g., 'zh-CN', 'en-US'
}

export function useBrowserTTS(options: UseBrowserTTSOptions = {}) {
  const {
    onStart,
    onEnd,
    onError,
    rate = 1.0,
    pitch = 1.0,
    volume = 1.0,
    lang = 'zh-CN',
  } = options;

  const [isSpeaking, setIsSpeaking] = useState(false);
  const [isPaused, setIsPaused] = useState(false);
  const [availableVoices, setAvailableVoices] = useState<SpeechSynthesisVoice[]>([]);
  const utteranceRef = useRef<SpeechSynthesisUtterance | null>(null);

  // Load available voices
  useEffect(() => {
    if (typeof window === 'undefined' || !window.speechSynthesis) {
      return;
    }

    const loadVoices = () => {
      const voices = window.speechSynthesis.getVoices();
      setAvailableVoices(voices);
    };

    loadVoices();

    // Some browsers load voices asynchronously
    if (window.speechSynthesis.onvoiceschanged !== undefined) {
      window.speechSynthesis.onvoiceschanged = loadVoices;
    }

    return () => {
      if (window.speechSynthesis.onvoiceschanged !== undefined) {
        window.speechSynthesis.onvoiceschanged = null;
      }
    };
  }, []);

  const speak = useCallback(
    (text: string, voiceURI?: string) => {
      if (typeof window === 'undefined' || !window.speechSynthesis) {
        onError?.('浏览器不支持 Web Speech API');
        return;
      }

      // Cancel any ongoing speech
      window.speechSynthesis.cancel();

      const utterance = new SpeechSynthesisUtterance(text);
      utterance.rate = rate;
      utterance.pitch = pitch;
      utterance.volume = volume;
      utterance.lang = lang;

      // Set voice if specified
      if (voiceURI) {
        const voice = availableVoices.find((v) => v.voiceURI === voiceURI);
        if (voice) {
          utterance.voice = voice;
        }
      }

      utterance.onstart = () => {
        setIsSpeaking(true);
        setIsPaused(false);
        onStart?.();
      };

      utterance.onend = () => {
        setIsSpeaking(false);
        setIsPaused(false);
        utteranceRef.current = null;
        onEnd?.();
      };

      utterance.onerror = (event) => {
        setIsSpeaking(false);
        setIsPaused(false);
        utteranceRef.current = null;
        onError?.(event.error);
      };

      utterance.onpause = () => {
        setIsPaused(true);
      };

      utterance.onresume = () => {
        setIsPaused(false);
      };

      utteranceRef.current = utterance;
      window.speechSynthesis.speak(utterance);
    },
    [rate, pitch, volume, lang, availableVoices, onStart, onEnd, onError],
  );

  const pause = useCallback(() => {
    if (typeof window !== 'undefined' && window.speechSynthesis) {
      window.speechSynthesis.pause();
    }
  }, []);

  const resume = useCallback(() => {
    if (typeof window !== 'undefined' && window.speechSynthesis) {
      window.speechSynthesis.resume();
    }
  }, []);

  const cancel = useCallback(() => {
    if (typeof window !== 'undefined' && window.speechSynthesis) {
      window.speechSynthesis.cancel();
      setIsSpeaking(false);
      setIsPaused(false);
      utteranceRef.current = null;
    }
  }, []);

  return {
    speak,
    pause,
    resume,
    cancel,
    isSpeaking,
    isPaused,
    availableVoices,
  };
}