elevenlabs-cli 0.1.8

Unofficial CLI for ElevenLabs text-to-speech API
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

//! Text-to-Speech CLI arguments

use clap::Args;

/// Text-to-Speech arguments
#[derive(Args)]
pub struct TextToSpeechArgs {
    /// Text to convert to speech (or use --file)
    #[arg(value_name = "TEXT")]
    pub text: Option<String>,

    /// Read text from file
    #[arg(short = 'i', long, value_name = "FILE")]
    pub file: Option<String>,

    /// Voice ID to use (default: Brian)
    #[arg(long, default_value = "Brian")]
    pub voice: String,

    /// Model to use
    #[arg(short, long, default_value = "eleven_multilingual_v2")]
    pub model: String,

    /// Output file path
    #[arg(short, long, value_name = "OUTPUT")]
    pub output: Option<String>,

    /// Play audio after generation
    #[arg(long)]
    pub play: bool,

    /// Output audio device name
    /// Use --list-output-devices to see available devices
    #[arg(long, value_name = "DEVICE")]
    pub output_device: Option<String>,

    /// List available output audio devices
    #[arg(long)]
    pub list_output_devices: bool,

    /// Stability (0.0-1.0)
    #[arg(long, value_name = "0.0-1.0")]
    pub stability: Option<f32>,

    /// Similarity boost (0.0-1.0)
    #[arg(long, value_name = "0.0-1.0")]
    pub similarity_boost: Option<f32>,

    /// Style (0.0-1.0)
    #[arg(long, value_name = "0.0-1.0")]
    pub style: Option<f32>,

    /// Use speaker boost
    #[arg(long)]
    pub speaker_boost: bool,

    /// Language code (e.g., en, es, fr)
    #[arg(long, value_name = "CODE")]
    pub language: Option<String>,

    /// Seed for deterministic generation
    #[arg(long, value_name = "INT")]
    pub seed: Option<u32>,
}

/// TTS with Timestamps arguments
#[derive(Args)]
pub struct TtsTimestampsArgs {
    /// Text to convert to speech (or use --file)
    #[arg(value_name = "TEXT")]
    pub text: Option<String>,

    /// Read text from file
    #[arg(short = 'i', long, value_name = "FILE")]
    pub file: Option<String>,

    /// Voice ID to use
    #[arg(long, default_value = "Brian")]
    pub voice: String,

    /// Model to use
    #[arg(long, default_value = "eleven_multilingual_v2")]
    pub model: String,

    /// Output file path
    #[arg(long, value_name = "OUTPUT")]
    pub output: Option<String>,

    /// Output format
    #[arg(long, default_value = "mp3_44100_128")]
    pub output_format: String,

    /// Output subtitle file (SRT/VTT)
    #[arg(long, value_name = "FILE")]
    pub subtitles: Option<String>,

    /// Enable logging (default: true)
    #[arg(long)]
    pub enable_logging: Option<bool>,

    /// Latency optimization (0-4)
    #[arg(long, value_name = "0-4")]
    pub latency: Option<u8>,
}

/// TTS Streaming arguments
#[derive(Args)]
pub struct TtsStreamArgs {
    /// Text to convert to speech
    #[arg(value_name = "TEXT")]
    pub text: String,

    /// Voice ID to use
    #[arg(long, default_value = "Brian")]
    pub voice: String,

    /// Model to use
    #[arg(long, default_value = "eleven_multilingual_v2")]
    pub model: String,

    /// Output file path
    #[arg(long, value_name = "OUTPUT")]
    pub output: Option<String>,

    /// Play audio after generation
    #[arg(long)]
    pub play: bool,

    /// Output audio device name
    /// Use --list-output-devices to see available devices
    #[arg(long, value_name = "DEVICE")]
    pub output_device: Option<String>,

    /// List available output audio devices
    #[arg(long)]
    pub list_output_devices: bool,

    /// Latency optimization (0-4)
    #[arg(long, value_name = "0-4")]
    pub latency: Option<u8>,

    /// Output format
    #[arg(long, default_value = "mp3_44100_128")]
    pub output_format: String,

    /// Stability (0.0-1.0)
    #[arg(long, value_name = "FLOAT")]
    pub stability: Option<f32>,

    /// Similarity boost (0.0-1.0)
    #[arg(long, value_name = "FLOAT")]
    pub similarity_boost: Option<f32>,
}