Hugging Face's logo

Spaces:
teralomaniac
/
sillytavern
Build error

App Files Community
sillytavern
File size: 4,651 Bytes 
70023bd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
import { getRequestHeaders } from "../../../script.js"
import { getApiUrl } from "../../extensions.js"
import { doExtrasFetch, modules } from "../../extensions.js"
import { getPreviewString } from "./index.js"

export { EdgeTtsProvider }

class EdgeTtsProvider {
    //########//
    // Config //
    //########//

    settings
    voices = []
    separator = ' . '
    audioElement = document.createElement('audio')

    defaultSettings = {
        voiceMap: {},
        rate: 0,
    }

    get settingsHtml() {
        let html = `Microsoft Edge TTS Provider<br>
        <label for="edge_tts_rate">Rate: <span id="edge_tts_rate_output"></span></label>
        <input id="edge_tts_rate" type="range" value="${this.defaultSettings.rate}" min="-100" max="100" step="1" />`
        return html
    }

    onSettingsChange() {
        this.settings.rate = Number($('#edge_tts_rate').val());
        $('#edge_tts_rate_output').text(this.settings.rate);
    }

    loadSettings(settings) {
        // Pupulate Provider UI given input settings
        if (Object.keys(settings).length == 0) {
            console.info("Using default TTS Provider settings")
        }

        // Only accept keys defined in defaultSettings
        this.settings = this.defaultSettings

        for (const key in settings) {
            if (key in this.settings) {
                this.settings[key] = settings[key]
            } else {
                throw `Invalid setting passed to TTS Provider: ${key}`
            }
        }

        $('#edge_tts_rate').val(this.settings.rate || 0);
        $('#edge_tts_rate_output').text(this.settings.rate || 0);

        console.info("Settings loaded")
    }


    async onApplyClick() {
        return
    }

    //#################//
    //  TTS Interfaces //
    //#################//

    async getVoice(voiceName) {
        if (this.voices.length == 0) {
            this.voices = await this.fetchTtsVoiceIds()
        }
        const match = this.voices.filter(
            voice => voice.name == voiceName
        )[0]
        if (!match) {
            throw `TTS Voice name ${voiceName} not found`
        }
        return match
    }

    async generateTts(text, voiceId) {
        const response = await this.fetchTtsGeneration(text, voiceId)
        return response
    }

    //###########//
    // API CALLS //
    //###########//
    async fetchTtsVoiceIds() {
        throwIfModuleMissing()

        const url = new URL(getApiUrl());
        url.pathname = `/api/edge-tts/list`
        const response = await doExtrasFetch(url)
        if (!response.ok) {
            throw new Error(`HTTP ${response.status}: ${await response.text()}`)
        }
        let responseJson = await response.json()
        responseJson = responseJson
            .sort((a, b) => a.Locale.localeCompare(b.Locale) || a.ShortName.localeCompare(b.ShortName))
            .map(x => ({ name: x.ShortName, voice_id: x.ShortName, preview_url: false, lang: x.Locale }));
        return responseJson
    }


    async previewTtsVoice(id) {
        this.audioElement.pause();
        this.audioElement.currentTime = 0;
        const voice = await this.getVoice(id);
        const text = getPreviewString(voice.lang);
        const response = await this.fetchTtsGeneration(text, id)
        if (!response.ok) {
            throw new Error(`HTTP ${response.status}: ${await response.text()}`)
        }

        const audio = await response.blob();
        const url = URL.createObjectURL(audio);
        this.audioElement.src = url;
        this.audioElement.play();
    }

    async fetchTtsGeneration(inputText, voiceId) {
        throwIfModuleMissing()

        console.info(`Generating new TTS for voice_id ${voiceId}`)
        const url = new URL(getApiUrl());
        url.pathname = `/api/edge-tts/generate`;
        const response = await doExtrasFetch(url,
            {
                method: 'POST',
                headers: getRequestHeaders(),
                body: JSON.stringify({
                    "text": inputText,
                    "voice": voiceId,
                    "rate": Number(this.settings.rate),
                })
            }
        )
        if (!response.ok) {
            toastr.error(response.statusText, 'TTS Generation Failed');
            throw new Error(`HTTP ${response.status}: ${await response.text()}`);
        }
        return response
    }
}
function throwIfModuleMissing() {
    if (!modules.includes('edge-tts')) {
        toastr.error(`Edge TTS module not loaded. Add edge-tts to enable-modules and restart the Extras API.`)
        throw new Error(`Edge TTS module not loaded.`)
    }
}