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
//! Speech-to-Text CLI arguments
use clap::Args;
/// Speech-to-Text arguments
#[derive(Args)]
pub struct SpeechToTextArgs {
/// Audio file to transcribe
#[arg(value_name = "FILE")]
pub file: Option<String>,
/// Record audio from microphone (use with --duration)
#[arg(long)]
pub record: bool,
/// Recording duration in seconds (use with --record)
#[arg(long, default_value = "5")]
pub duration: f32,
/// Input audio device name (for recording)
/// Use --list-input-devices to see available devices
#[arg(long, value_name = "DEVICE")]
pub input_device: Option<String>,
/// List available input audio devices
#[arg(long)]
pub list_input_devices: bool,
/// Model to use
#[arg(short, long, default_value = "scribe_v1")]
pub model: String,
/// Language code (auto-detected if not specified)
#[arg(short, long, value_name = "CODE")]
pub language: Option<String>,
/// Tag audio events
#[arg(long, default_value = "true")]
pub tag_audio_events: bool,
/// Number of speakers (for diarization)
#[arg(long, value_name = "INT")]
pub num_speakers: Option<u32>,
/// Timestamps granularity (none, word, character)
#[arg(long, default_value = "word")]
pub timestamps: String,
/// Enable speaker diarization
#[arg(long)]
pub diarize: bool,
/// Output format (json, txt, srt, vtt)
#[arg(short, long, default_value = "txt")]
pub format: String,
/// Output file (default: stdout)
#[arg(short, long, value_name = "FILE")]
pub output: Option<String>,
}