msedge-tts 0.1.0

This library is a wrapper of **MSEdge Read aloud** function API. You can use it to synthesize text to speech with many voices MS provided.
Documentation 
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

//! Synthesis Client

use super::{
    build_config_message, build_ssml_message, process_message, websocket_connect,
    websocket_connect_asnyc, AudioMetadata, ProcessedMessage, SpeechConfig, WebSocketStream,
    WebSocketStreamAsync,
};
use crate::error::Result;

/// Sync Client
pub struct MSEdgeTTSClient(WebSocketStream);

impl MSEdgeTTSClient {
    /// Create a new sync Client
    pub fn connect() -> Result<Self> {
        Ok(Self(websocket_connect()?))
    }

    /// Synthesize text to speech with a [SpeechConfig] synchronously
    pub fn synthesize(&mut self, text: &str, config: &SpeechConfig) -> Result<SynthesizedAudio> {
        let config_message = build_config_message(config);
        let ssml_message = build_ssml_message(text, config);
        self.0.send(config_message)?;
        self.0.send(ssml_message)?;

        let mut audio_bytes = Vec::new();
        let mut audio_metadata = Vec::new();
        let mut turn_start = false;
        let mut response = false;
        let mut turn_end = false;
        loop {
            if turn_end {
                break;
            }

            let message = self.0.read()?;
            let message = process_message(message, &mut turn_start, &mut response, &mut turn_end)?;
            if let Some(message) = message {
                match message {
                    ProcessedMessage::AudioBytes(payload) => {
                        audio_bytes.push(payload);
                    }
                    ProcessedMessage::AudioMetadata(metadata) => {
                        audio_metadata.extend(metadata);
                    }
                }
            }
        }

        let audio_bytes = audio_bytes
            .iter()
            .flat_map(|(bytes, index)| &bytes[*index..])
            .copied()
            .collect();

        Ok(SynthesizedAudio {
            audio_format: config.audio_format.clone(),
            audio_bytes,
            audio_metadata,
        })
    }
}

/// Async Client
pub struct MSEdgeTTSClientAsync(WebSocketStreamAsync);

impl MSEdgeTTSClientAsync {
    /// Create a new async Client
    pub async fn connect_async() -> Result<Self> {
        Ok(Self(websocket_connect_asnyc().await?))
    }

    /// Synthesize text to speech with a [SpeechConfig] asynchronously
    pub async fn synthesize_async(
        &mut self,
        text: &str,
        config: &SpeechConfig,
    ) -> Result<SynthesizedAudio> {
        use futures_util::{SinkExt, StreamExt};

        let config_message = build_config_message(config);
        let ssml_message = build_ssml_message(text, config);
        self.0.send(config_message).await?;
        self.0.send(ssml_message).await?;

        let mut audio_bytes = Vec::new();
        let mut audio_metadata = Vec::new();
        let mut turn_start = false;
        let mut response = false;
        let mut turn_end = false;
        loop {
            if turn_end {
                break;
            }

            if let Some(message) = self.0.next().await {
                let message = message?;
                let response =
                    process_message(message, &mut turn_start, &mut response, &mut turn_end)?;
                if let Some(response) = response {
                    match response {
                        ProcessedMessage::AudioBytes(payload) => {
                            audio_bytes.push(payload);
                        }
                        ProcessedMessage::AudioMetadata(metadata) => {
                            audio_metadata.extend(metadata);
                        }
                    }
                }
            }
        }

        let audio_bytes = audio_bytes
            .iter()
            .flat_map(|(bytes, index)| &bytes[*index..])
            .copied()
            .collect();

        Ok(SynthesizedAudio {
            audio_format: config.audio_format.clone(),
            audio_bytes,
            audio_metadata,
        })
    }
}

/// Synthesized Audio and Metadata
#[derive(Debug)]
pub struct SynthesizedAudio {
    pub audio_format: String,
    pub audio_bytes: Vec<u8>,
    pub audio_metadata: Vec<AudioMetadata>,
}