File size: 2,173 Bytes
7495571
3ed3b5a
 
 
7495571
 
3ed3b5a
 
 
 
 
7495571
 
3ed3b5a
 
 
 
 
 
 
 
 
7495571
3ed3b5a
 
 
 
7495571
3ed3b5a
 
 
 
7495571
 
3ed3b5a
 
7495571
3ed3b5a
 
 
7495571
 
 
3ed3b5a
 
 
 
 
 
 
 
 
7495571
3ed3b5a
7495571
 
3ed3b5a
 
7495571
 
3ed3b5a
 
 
 
7495571
 
 
 
 
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
import logging
import os
import time
import numpy as np
import soundfile as sf
from typing import Optional, Generator, Tuple, List
from abc import ABC, abstractmethod

# Configure logging
logger = logging.getLogger(__name__)


class TTSBase(ABC):
    """Base class for all TTS engines
    
    This abstract class defines the interface that all TTS engines must implement.
    """
    
    def __init__(self, lang_code: str = 'z'):
        """Initialize the TTS engine
        
        Args:
            lang_code (str): Language code for the engine
        """
        self.lang_code = lang_code
    
    @abstractmethod
    def generate_speech(self, text: str, voice: str = 'default', speed: float = 1.0) -> Optional[str]:
        """Generate speech from text
        
        Args:
            text (str): Input text to synthesize
            voice (str): Voice ID to use
            speed (float): Speech speed multiplier
            
        Returns:
            Optional[str]: Path to the generated audio file or None if generation fails
        """
        pass
    
    @abstractmethod
    def generate_speech_stream(self, text: str, voice: str = 'default', speed: float = 1.0) -> Generator[Tuple[int, np.ndarray], None, None]:
        """Generate speech stream from text
        
        Args:
            text (str): Input text to synthesize
            voice (str): Voice ID to use
            speed (float): Speech speed multiplier
            
        Yields:
            tuple: (sample_rate, audio_data) pairs for each segment
        """
        pass
    
    def _generate_output_path(self, prefix: str = "tts", extension: str = "wav") -> str:
        """Generate a unique output path for the audio file
        
        Args:
            prefix (str): Prefix for the filename
            extension (str): File extension
            
        Returns:
            str: Path to the output file
        """
        timestamp = int(time.time() * 1000)
        filename = f"{prefix}_{timestamp}.{extension}"
        output_dir = os.path.join(os.getcwd(), "output")
        os.makedirs(output_dir, exist_ok=True)
        return os.path.join(output_dir, filename)