[go: up one dir, main page]

tts 0.6.1

High-level Text-To-Speech (TTS) interface
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
152
153
154
155
156
157
158
159

#[cfg(windows)]
use log::{info, trace};

use tts_winrt_bindings::windows::media::core::MediaSource;
use tts_winrt_bindings::windows::media::playback::{
    MediaPlaybackItem, MediaPlaybackList, MediaPlaybackState, MediaPlayer,
};
use tts_winrt_bindings::windows::media::speech_synthesis::SpeechSynthesizer;

use crate::{Backend, Error, Features};

impl From<winrt::Error> for Error {
    fn from(e: winrt::Error) -> Self {
        Error::WinRT(e)
    }
}

pub struct WinRT {
    synth: SpeechSynthesizer,
    player: MediaPlayer,
    playback_list: MediaPlaybackList,
}

impl WinRT {
    pub fn new() -> std::result::Result<Self, Error> {
        info!("Initializing WinRT backend");
        let playback_list = MediaPlaybackList::new()?;
        let player = MediaPlayer::new()?;
        player.set_auto_play(true)?;
        player.set_source(&playback_list)?;
        Ok(Self {
            synth: SpeechSynthesizer::new()?,
            player: player,
            playback_list: playback_list,
        })
    }

    fn reinit_player(&mut self) -> std::result::Result<(), Error> {
        self.playback_list = MediaPlaybackList::new()?;
        self.player = MediaPlayer::new()?;
        self.player.set_auto_play(true)?;
        self.player.set_source(&self.playback_list)?;
        Ok(())
    }
}

impl Backend for WinRT {
    fn supported_features(&self) -> Features {
        Features {
            stop: true,
            rate: true,
            pitch: true,
            volume: true,
            is_speaking: true,
        }
    }

    fn speak(&mut self, text: &str, interrupt: bool) -> std::result::Result<(), Error> {
        trace!("speak({}, {})", text, interrupt);
        if interrupt {
            self.stop()?;
        }
        let stream = self.synth.synthesize_text_to_stream_async(text)?.get()?;
        let content_type = stream.content_type()?;
        let source = MediaSource::create_from_stream(stream, content_type)?;
        let item = MediaPlaybackItem::create(source)?;
        let state = self.player.playback_session()?.playback_state()?;
        if state == MediaPlaybackState::Paused {
            let index = self.playback_list.current_item_index()?;
            let total = self.playback_list.items()?.size()?;
            if total != 0 && index == total - 1 {
                self.reinit_player()?;
            }
        }
        self.playback_list.items()?.append(item)?;
        if !self.is_speaking()? {
            self.player.play()?;
        }
        Ok(())
    }

    fn stop(&mut self) -> std::result::Result<(), Error> {
        trace!("stop()");
        self.reinit_player()?;
        Ok(())
    }

    fn min_rate(&self) -> f32 {
        0.5
    }

    fn max_rate(&self) -> f32 {
        6.0
    }

    fn normal_rate(&self) -> f32 {
        1.
    }

    fn get_rate(&self) -> std::result::Result<f32, Error> {
        let rate = self.synth.options()?.speaking_rate()?;
        Ok(rate as f32)
    }

    fn set_rate(&mut self, rate: f32) -> std::result::Result<(), Error> {
        self.synth.options()?.set_speaking_rate(rate.into())?;
        Ok(())
    }

    fn min_pitch(&self) -> f32 {
        0.
    }

    fn max_pitch(&self) -> f32 {
        2.
    }

    fn normal_pitch(&self) -> f32 {
        1.
    }

    fn get_pitch(&self) -> std::result::Result<f32, Error> {
        let pitch = self.synth.options()?.audio_pitch()?;
        Ok(pitch as f32)
    }

    fn set_pitch(&mut self, pitch: f32) -> std::result::Result<(), Error> {
        self.synth.options()?.set_audio_pitch(pitch.into())?;
        Ok(())
    }

    fn min_volume(&self) -> f32 {
        0.
    }

    fn max_volume(&self) -> f32 {
        1.
    }

    fn normal_volume(&self) -> f32 {
        1.
    }

    fn get_volume(&self) -> std::result::Result<f32, Error> {
        let volume = self.synth.options()?.audio_volume()?;
        Ok(volume as f32)
    }

    fn set_volume(&mut self, volume: f32) -> std::result::Result<(), Error> {
        self.synth.options()?.set_audio_volume(volume.into())?;
        Ok(())
    }

    fn is_speaking(&self) -> std::result::Result<bool, Error> {
        let state = self.player.playback_session()?.playback_state()?;
        let playing = state == MediaPlaybackState::Opening || state == MediaPlaybackState::Playing;
        Ok(playing)
    }
}