autoagents-speech 0.3.7

Speech (TTS/STT) provider abstractions for AutoAgents
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

use thiserror::Error;

/// TTS-related errors
#[derive(Error, Debug)]
pub enum TTSError {
    /// Provider-specific error
    #[error(
        "TTS provider error: {0}\nProvider: {1}\nDetails: This error originated from the TTS provider implementation"
    )]
    ProviderError(String, String),

    /// Invalid voice data
    #[error(
        "Invalid voice data: {0}\nContext: {1}\nSuggestion: Ensure voice embeddings are properly downloaded from HuggingFace"
    )]
    InvalidVoiceData(String, String),

    /// Audio generation failed
    #[error(
        "Audio generation failed: {0}\nInput text length: {1} characters\nVoice: {2}\nSuggestion: Try shorter text or check model initialization"
    )]
    GenerationFailed(String, usize, String),

    /// Streaming not supported
    #[error(
        "Streaming not supported by this provider\nProvider: {0}\nSuggestion: Use generate_speech() instead of generate_speech_stream()"
    )]
    StreamingNotSupported(String),

    /// IO error
    #[error(
        "IO error during TTS operation: {0}\nOperation: {1}\nPath: {2}\nSuggestion: Check file permissions and disk space"
    )]
    IoError(std::io::Error, String, String),

    /// Model not found
    #[error(
        "Model not found: '{0}'\nModel path: {1}\nSuggestion: Ensure model is downloaded from HuggingFace. Check HUGGINGFACE_TOKEN environment variable"
    )]
    ModelNotFound(String, String),

    /// Other errors
    #[error("TTS error: {0}\nContext: {1}")]
    Other(String, String),
}

/// Result type for TTS operations
pub type TTSResult<T> = Result<T, TTSError>;

/// STT-related errors
#[derive(Error, Debug)]
pub enum STTError {
    /// Provider-specific error
    #[error(
        "STT provider error: {0}\nProvider: {1}\nDetails: This error originated from the STT provider implementation"
    )]
    ProviderError(String, String),

    /// Transcription failed
    #[error(
        "Transcription failed: {0}\nAudio duration: {1}s\nSample rate: {2}Hz\nSuggestion: Check audio quality or try a different model"
    )]
    TranscriptionFailed(String, f32, u32),

    /// Streaming not supported
    #[error(
        "Streaming not supported by this provider\nProvider: {0}\nSuggestion: Use transcribe() instead of transcribe_stream()"
    )]
    StreamingNotSupported(String),

    /// Invalid audio format
    #[error(
        "Invalid audio format: {0}\nExpected sample rate: {1}Hz, Got: {2}Hz\nExpected channels: {3}, Got: {4}\nSuggestion: Resample audio to the correct format"
    )]
    InvalidAudioFormat(String, u32, u32, u16, u16),

    /// IO error
    #[error(
        "IO error during STT operation: {0}\nOperation: {1}\nPath: {2}\nSuggestion: Check file permissions and disk space"
    )]
    IoError(std::io::Error, String, String),

    /// Model not found
    #[error(
        "Model not found: '{0}'\nModel path: {1}\nSuggestion: Ensure model is downloaded from HuggingFace"
    )]
    ModelNotFound(String, String),

    /// Other errors
    #[error("STT error: {0}\nContext: {1}")]
    Other(String, String),
}

/// Result type for STT operations
pub type STTResult<T> = Result<T, STTError>;