deepgram 0.9.2

Community Rust SDK for Deepgram's automated speech recognition APIs.
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
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
160
161
162
163
164
165
166
167
168
169
170
171

//! Stream Response module

use serde::{Deserialize, Serialize};

/// A single transcribed word.
///
/// See the [Deepgram API Reference][api] for more info.
///
/// [api]: https://developers.deepgram.com/api-reference/#transcription-prerecorded
#[derive(Debug, Serialize, Deserialize)]
pub struct Word {
    #[allow(missing_docs)]
    pub word: String,

    #[allow(missing_docs)]
    pub start: f64,

    #[allow(missing_docs)]
    pub end: f64,

    #[allow(missing_docs)]
    pub confidence: f64,

    #[allow(missing_docs)]
    pub speaker: Option<i32>,

    #[allow(missing_docs)]
    pub punctuated_word: Option<String>,

    #[allow(missing_docs)]
    pub language: Option<String>,
}

/// Transcript alternatives.
///
/// See the [Deepgram API Reference][api] for more info.
///
/// [api]: https://developers.deepgram.com/api-reference/#transcription-prerecorded
#[derive(Debug, Serialize, Deserialize)]
pub struct Alternatives {
    #[allow(missing_docs)]
    pub transcript: String,

    #[allow(missing_docs)]
    pub words: Vec<Word>,

    #[allow(missing_docs)]
    pub confidence: f64,

    #[allow(missing_docs)]
    #[serde(default)]
    pub languages: Vec<String>,
}

/// Transcription results for a single audio channel.
///
/// See the [Deepgram API Reference][api]
/// and the [Deepgram Multichannel feature docs][docs] for more info.
///
/// [api]: https://developers.deepgram.com/api-reference/#transcription-prerecorded
/// [docs]: https://developers.deepgram.com/documentation/features/multichannel/
#[derive(Debug, Serialize, Deserialize)]
pub struct Channel {
    #[allow(missing_docs)]
    pub alternatives: Vec<Alternatives>,
}

/// Modle info
#[derive(Debug, Serialize, Deserialize)]
pub struct ModelInfo {
    #[allow(missing_docs)]
    pub name: String,

    #[allow(missing_docs)]
    pub version: String,

    #[allow(missing_docs)]
    pub arch: String,
}

/// Metadata about the transcription.
///
/// See the [Deepgram API Reference][api] for more info.
///
/// [api]: https://developers.deepgram.com/api-reference/#transcription-prerecorded
#[derive(Debug, Serialize, Deserialize)]
pub struct Metadata {
    #[allow(missing_docs)]
    pub request_id: String,

    #[allow(missing_docs)]
    pub model_info: ModelInfo,

    #[allow(missing_docs)]
    pub model_uuid: String,
}

/// Possible websocket message types
#[derive(Debug, Serialize, Deserialize)]
#[serde(untagged)]
#[non_exhaustive]
pub enum StreamResponse {
    #[allow(missing_docs)]
    TranscriptResponse {
        #[allow(missing_docs)]
        #[serde(rename = "type")]
        type_field: String,

        #[allow(missing_docs)]
        start: f64,

        #[allow(missing_docs)]
        duration: f64,

        #[allow(missing_docs)]
        is_final: bool,

        #[allow(missing_docs)]
        speech_final: bool,

        #[allow(missing_docs)]
        from_finalize: bool,

        #[allow(missing_docs)]
        channel: Channel,

        #[allow(missing_docs)]
        metadata: Metadata,

        #[allow(missing_docs)]
        channel_index: Vec<i32>,
    },
    #[allow(missing_docs)]
    TerminalResponse {
        #[allow(missing_docs)]
        request_id: String,

        #[allow(missing_docs)]
        created: String,

        #[allow(missing_docs)]
        duration: f64,

        #[allow(missing_docs)]
        channels: u32,
    },
    #[allow(missing_docs)]
    SpeechStartedResponse {
        #[allow(missing_docs)]
        #[serde(rename = "type")]
        type_field: String,

        #[allow(missing_docs)]
        channel: Vec<u8>,

        #[allow(missing_docs)]
        timestamp: f64,
    },
    #[allow(missing_docs)]
    UtteranceEndResponse {
        #[allow(missing_docs)]
        #[serde(rename = "type")]
        type_field: String,

        #[allow(missing_docs)]
        channel: Vec<u8>,

        #[allow(missing_docs)]
        last_word_end: f64,
    },
}