File size: 3,999 Bytes
860a086 | 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 | from fastapi import FastAPI, HTTPException, Query
from fastapi.responses import FileResponse
from fastapi.staticfiles import StaticFiles
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
import os
import uuid
import tempfile
from typing import Optional
import soundfile as sf
# Import your TTS dependencies
from kokoro import KPipeline
# Initialize the TTS pipeline
pipeline = KPipeline(lang_code='a') # Make sure lang_code matches voice
# Initialize FastAPI app
app = FastAPI(title="Kokoro TTS API Service")
# Add CORS middleware to allow frontend requests
app.add_middleware(
CORSMiddleware,
allow_origins=["*"], # In production, replace with your domains
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
# Mount static files directory
app.mount("/static", StaticFiles(directory="static"), name="static")
# Create temp directory to store audio files
TEMP_DIR = tempfile.gettempdir()
os.makedirs(TEMP_DIR, exist_ok=True)
def tts(text, file_name, voice='af_bella', speed=0.9):
"""
Generate speech from text using Kokoro TTS
Args:
text (str): Text to convert to speech
file_name (str): Path to save the output .wav file
voice (str): Voice to use for TTS
speed (float): Speed of speech
Returns:
str: Path to the generated audio file
"""
try:
generator = pipeline(
text, voice=voice,
speed=speed, split_pattern=None
)
for i, (gs, ps, audio) in enumerate(generator):
sf.write(file_name, audio, 24000) # save audio file
return file_name
except Exception as e:
raise Exception(f"TTS generation failed: {str(e)}")
class TTSRequest(BaseModel):
text: str
voice: str = "af_bella"
speed: float = 0.9
@app.post("/tts/")
async def text_to_speech(request: TTSRequest):
"""
Convert text to speech and return a .wav file
"""
try:
# Generate a unique filename
filename = f"{uuid.uuid4()}.wav"
output_path = os.path.join(TEMP_DIR, filename)
# Generate speech using your TTS function
tts(request.text, output_path, request.voice, request.speed)
# Return the audio file
return FileResponse(
path=output_path,
filename=filename,
media_type="audio/wav"
)
except Exception as e:
raise HTTPException(status_code=500, detail=f"TTS generation failed: {str(e)}")
@app.get("/tts-get/")
async def text_to_speech_get(
text: str = Query(..., description="Text to convert to speech"),
voice: str = Query("af_bella", description="Voice to use for TTS"),
speed: float = Query(0.9, description="Speed of speech (0.5-1.5)")
):
"""
GET endpoint for text-to-speech conversion
"""
try:
# Generate a unique filename
filename = f"{uuid.uuid4()}.wav"
output_path = os.path.join(TEMP_DIR, filename)
# Generate speech using your TTS function
tts(text, output_path, voice, speed)
# Return the audio file
return FileResponse(
path=output_path,
filename=filename,
media_type="audio/wav"
)
except Exception as e:
raise HTTPException(status_code=500, detail=f"TTS generation failed: {str(e)}")
@app.get("/voices/")
async def available_voices():
"""
Return a list of available voices
"""
# This is a placeholder - you should replace with actual available voices
# from your kokoro library
return {
"voices": ["af_bella"], # Add other available voices here
"default": "af_bella"
}
@app.get("/")
async def root():
"""
Serve the frontend HTML
"""
return FileResponse('static/index.html') |