roder-api 0.1.0

Agentic software development tools and SDKs for Roder.
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
172
173

use std::collections::BTreeMap;

use serde::{Deserialize, Serialize};

use crate::extension::{SpeechSynthesizerId, SpeechTranscriberId};
use crate::inference::ProviderAuthType;

#[derive(Debug, Clone, Copy, Default, Serialize, Deserialize, PartialEq, Eq)]
#[serde(rename_all = "camelCase")]
pub struct SpeechCapabilities {
    pub batch: bool,
    pub streaming: bool,
    pub diarization: bool,
    pub timestamps: bool,
    pub language_hints: bool,
    pub prompt: bool,
}

#[derive(Debug, Clone, Copy, Default, Serialize, Deserialize, PartialEq, Eq)]
#[serde(rename_all = "camelCase")]
pub struct SpeechSynthesisCapabilities {
    pub batch: bool,
    pub streaming: bool,
    pub builtin_voices: bool,
    pub voice_design: bool,
    pub voice_clone: bool,
    pub prompt: bool,
}

#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
pub struct SpeechProviderMetadata {
    pub name: String,
    pub description: Option<String>,
    pub auth_type: ProviderAuthType,
    pub auth_label: Option<String>,
    pub auth_configured: Option<bool>,
    pub recommended: bool,
    pub sort_order: i32,
}

impl SpeechProviderMetadata {
    pub fn local(name: impl Into<String>) -> Self {
        Self {
            name: name.into(),
            description: None,
            auth_type: ProviderAuthType::None,
            auth_label: None,
            auth_configured: Some(true),
            recommended: false,
            sort_order: 100,
        }
    }
}

#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
pub struct SpeechModelDescriptor {
    pub id: String,
    pub name: String,
    pub description: Option<String>,
    pub capabilities: SpeechCapabilities,
}

#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
pub struct SpeechSynthesisModelDescriptor {
    pub id: String,
    pub name: String,
    pub description: Option<String>,
    pub capabilities: SpeechSynthesisCapabilities,
}

#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
pub struct SpeechAudio {
    pub bytes: Vec<u8>,
    pub mime_type: String,
    pub filename: Option<String>,
}

#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
pub struct SpeechTranscriptionRequest {
    pub model: String,
    pub audio: SpeechAudio,
    pub language: Option<String>,
    pub prompt: Option<String>,
    pub diarization: bool,
    #[serde(default)]
    pub metadata: BTreeMap<String, serde_json::Value>,
}

#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
pub struct SpeechSegment {
    pub text: String,
    pub start_millis: Option<u64>,
    pub end_millis: Option<u64>,
    pub speaker: Option<String>,
    pub confidence: Option<f32>,
}

#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
pub struct SpeechTranscriptionResult {
    pub text: String,
    pub language: Option<String>,
    pub duration_millis: Option<u64>,
    pub segments: Vec<SpeechSegment>,
    pub provider_response_id: Option<String>,
    #[serde(default)]
    pub metadata: serde_json::Value,
}

#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
pub struct SpeechSynthesisRequest {
    pub model: String,
    pub text: String,
    pub voice: Option<String>,
    pub audio_format: Option<String>,
    pub prompt: Option<String>,
    pub voice_sample: Option<SpeechAudio>,
    #[serde(default)]
    pub metadata: BTreeMap<String, serde_json::Value>,
}

#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
pub struct SpeechSynthesisResult {
    pub audio: SpeechAudio,
    pub duration_millis: Option<u64>,
    pub provider_response_id: Option<String>,
    #[serde(default)]
    pub metadata: serde_json::Value,
}

#[derive(Debug, Clone, Copy)]
pub struct SpeechProviderContext<'a> {
    pub provider_id: &'a str,
}

#[async_trait::async_trait]
pub trait SpeechTranscriber: Send + Sync + 'static {
    fn id(&self) -> SpeechTranscriberId;

    fn capabilities(&self) -> SpeechCapabilities;

    fn metadata(&self) -> SpeechProviderMetadata;

    async fn list_models(
        &self,
        ctx: SpeechProviderContext<'_>,
    ) -> anyhow::Result<Vec<SpeechModelDescriptor>>;

    async fn transcribe(
        &self,
        ctx: SpeechProviderContext<'_>,
        request: SpeechTranscriptionRequest,
    ) -> anyhow::Result<SpeechTranscriptionResult>;
}

#[async_trait::async_trait]
pub trait SpeechSynthesizer: Send + Sync + 'static {
    fn id(&self) -> SpeechSynthesizerId;

    fn capabilities(&self) -> SpeechSynthesisCapabilities;

    fn metadata(&self) -> SpeechProviderMetadata;

    async fn list_models(
        &self,
        ctx: SpeechProviderContext<'_>,
    ) -> anyhow::Result<Vec<SpeechSynthesisModelDescriptor>>;

    async fn synthesize(
        &self,
        ctx: SpeechProviderContext<'_>,
        request: SpeechSynthesisRequest,
    ) -> anyhow::Result<SpeechSynthesisResult>;
}