File size: 3,907 Bytes
224a44e d0b1d85 996d0ad 224a44e d0b1d85 996d0ad d0b1d85 224a44e d0b1d85 d638b54 224a44e d0b1d85 224a44e d0b1d85 224a44e d0b1d85 224a44e d0b1d85 996d0ad d0b1d85 996d0ad d0b1d85 224a44e d0b1d85 224a44e d0b1d85 224a44e d0b1d85 224a44e d0b1d85 224a44e d0b1d85 224a44e 996d0ad d0b1d85 224a44e 996d0ad d0b1d85 996d0ad 224a44e 996d0ad d0b1d85 996d0ad 224a44e d0b1d85 224a44e d0b1d85 996d0ad d0b1d85 996d0ad |
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 |
from fastapi import FastAPI, Query
import uvicorn
import requests
import os
from pydub import AudioSegment
from uuid import uuid4
app = FastAPI()
# ✅ Create directory to store audio files
AUDIO_DIR = "audio_files"
os.makedirs(AUDIO_DIR, exist_ok=True)
# ✅ Replace with your actual TTS API URL
TTS_API_URL = "https://hivecorp-s8test.hf.space/tts" # Change this
# 🔹 Function: Splitting long text into smaller chunks
def split_text(text, max_length=500):
"""Splits text into chunks of max_length characters"""
words = text.split()
chunks = []
current_chunk = []
current_length = 0
for word in words:
if current_length + len(word) + 1 > max_length:
chunks.append(" ".join(current_chunk))
current_chunk = []
current_length = 0
current_chunk.append(word)
current_length += len(word) + 1
if current_chunk:
chunks.append(" ".join(current_chunk))
return chunks
# 🔹 Function: Call external TTS API
def call_tts_api(text, voice):
"""Calls external TTS API and returns the saved MP3 filename."""
try:
response = requests.post(
TTS_API_URL,
json={"text": text, "voice": voice},
headers={"Content-Type": "application/json"}
)
data = response.json()
# ✅ Log response for debugging
print("TTS API Response:", data)
if "audio_url" in data:
audio_url = data["audio_url"]
filename = f"audio_{uuid4().hex}.mp3"
audio_path = os.path.join(AUDIO_DIR, filename)
# ✅ Download the MP3 file
with requests.get(audio_url, stream=True) as r:
r.raise_for_status()
with open(audio_path, "wb") as f:
for chunk in r.iter_content(chunk_size=8192):
f.write(chunk)
return audio_path # ✅ Return saved file path
else:
print("Error: Invalid TTS API response", data)
return None
except Exception as e:
print("TTS API Error:", e)
return None
# 🔹 Function: Merge multiple MP3s into one
def merge_audio(audio_files):
"""Merges multiple MP3 files into one final MP3."""
if not audio_files:
return None
final_audio = AudioSegment.empty()
for file in audio_files:
final_audio += AudioSegment.from_mp3(file)
final_filename = f"{AUDIO_DIR}/final_{uuid4().hex}.mp3"
final_audio.export(final_filename, format="mp3")
return final_filename
# ✅ API Endpoint: Generate Audio from Text
@app.post("/generate-audio")
def generate_audio(text: str = Query(...), voice: str = Query(...)):
"""Splits text, calls TTS API, merges audio, and returns the final MP3."""
chunks = split_text(text)
print("Total Chunks:", len(chunks))
audio_files = []
for chunk in chunks:
filename = call_tts_api(chunk, voice)
if filename:
audio_files.append(filename)
if not audio_files:
return {"error": "TTS API failed for all parts"}
final_audio = merge_audio(audio_files)
if final_audio:
return {"success": True, "audio_url": f"/download/{os.path.basename(final_audio)}"}
else:
return {"error": "Failed to merge audio files"}
# ✅ API Endpoint: Download the generated MP3
@app.get("/download/{filename}")
def download_file(filename: str):
"""Allows users to download the generated MP3 file."""
file_path = os.path.join(AUDIO_DIR, filename)
if os.path.exists(file_path):
return {"download_url": f"https://hivecorp-manager1.hf.space/audio_files/{filename}"}
return {"error": "File not found"}
# ✅ Ensure the app starts when running in Hugging Face Spaces
if __name__ == "__main__":
uvicorn.run(app, host="0.0.0.0", port=7860)
|