File size: 2,121 Bytes
84b088a
 
b3e5fcf
84b088a
 
 
 
 
 
7e0ec98
 
 
 
84b088a
 
 
 
5537343
7859e04
5537343
84b088a
 
 
 
 
35f9a40
84b088a
 
 
 
b3e5fcf
 
 
 
 
 
 
35f9a40
b3e5fcf
 
 
 
 
75f99e0
35f9a40
 
b3e5fcf
 
 
68a6d75
b3e5fcf
 
 
 
68a6d75
 
 
 
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
from fastapi import FastAPI, Query, HTTPException
from fastapi.responses import StreamingResponse
from fastapi.responses import FileResponse
from TTS.api import TTS
import os
from io import BytesIO
from typing import Generator

app = FastAPI()
import os

# By using XTTS you agree to CPML license https://coqui.ai/cpml
os.environ["COQUI_TOS_AGREED"] = "1"

# Initialize the TTS model
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2", gpu=False)  # Set gpu=True if you have GPU support

# Predefined path to the sample voice clone
FIXED_SPEAKER_WAV = "Bible Verses About Community.wav"

# Function to split text into chunks
def split_text(text: str, words_per_chunk: int = 20):
    words = text.split()
    return [' '.join(words[i:i + words_per_chunk]) for i in range(0, len(words), words_per_chunk)]



@app.post("/generate-audio/")
async def generate_audio(
    text: str = Query(..., description="The input text to convert to speech."),
    language: str = Query("en", description="Language code for TTS (e.g., 'en' for English).")):
    
        if not os.path.exists(FIXED_SPEAKER_WAV):
            raise HTTPException(status_code=400, detail="Fixed speaker WAV file not found.")

        if tts.is_multi_lingual and not language:
            raise ValueError("Language must be specified for multi-lingual models.")
        
            # Generate audio for each chunk and yield as bytes
        output_file = f"out.wav"
        try:
            tts.tts_to_file(
                    text=text,
                    file_path=output_file,
                    speaker_wav=FIXED_SPEAKER_WAV,
                    language=language
            )
            print(output_file)
            # Return the generated audio file as a response
            return FileResponse(output_file, media_type="audio/wav")

        except Exception as e:
            raise HTTPException(status_code=500, detail=f"Error generating audio: {str(e)}")
    
        # finally:
        #     # Clean up the generated file after the response is sent
        #     if os.path.exists(output_file):
        #         os.remove(output_file)