Update api.py

api.py

@@ -1,106 +1,81 @@
-import os
-import uuid
-import asyncio
-import unicodedata
-from fastapi import FastAPI, HTTPException
-from fastapi.responses import FileResponse
-from pydantic import BaseModel
-import edge_tts
-
-app = FastAPI(title="Edge TTS API", description="Microsoft Edge Neural TTS API")
-
-os.makedirs("tts_outputs", exist_ok=True)
-
-VOICES = {
-    "ar": {
-        "male": "ar-EG-ShakirNeural",
-        "female": "ar-EG-SalmaNeural"
-    },
-    "ar-sa": {
-        "female": "ar-SA-ZariyahNeural"
-    },
-    "en": {
-        "male": "en-US-GuyNeural",
-        "female": "en-US-AvaNeural"
-    },
-    "en-gb": {
-        "female": "en-GB-SoniaNeural"
-    },
-    "fr": {
-        "male": "fr-FR-HenriNeural",
-        "female": "fr-FR-DeniseNeural"
-    },
-    "de": {
-        "male": "de-DE-ConradNeural",
-        "female": "de-DE-KatjaNeural"
-    },
-    "es": {
-        "male": "es-ES-AlvaroNeural",
-        "female": "es-ES-ElviraNeural"
-    },
-    "it": {
-        "male": "it-IT-DiegoNeural",
-        "female": "it-IT-ElsaNeural"
-    },
-    "tr": {
-        "male": "tr-TR-AhmetNeural",
-        "female": "tr-TR-EmelNeural"
-    },
-    "ru": {
-        "male": "ru-RU-DmitryNeural",
-        "female": "ru-RU-SvetlanaNeural"
-    },
-    "hi": {
-        "male": "hi-IN-MadhurNeural",
-        "female": "hi-IN-SwaraNeural"
-    }
-}
-
-SUPPORTED_LANGUAGES = list(VOICES.keys())
-
-class TTSRequest(BaseModel):
-    text: str
-    language: str = "en"
-    gender: str = "female"
-    rate: str = "+0%"  # speed: -50%, -25%, +0%, +25%, +50%
-
-@app.get("/")
-def root():
-    return {"message": "Edge TTS API is running ✅"}
-
-@app.post("/tts")
-async def synthesize(req: TTSRequest):
-    text = unicodedata.normalize("NFC", req.text)
-
-    if not text.strip():
-        raise HTTPException(status_code=400, detail="Text cannot be empty.")
-    if req.language not in VOICES:
-        raise HTTPException(status_code=400, detail=f"Unsupported language. Choose from: {SUPPORTED_LANGUAGES}")
-    if req.gender not in ["male", "female"]:
-        raise HTTPException(status_code=400, detail="Gender must be 'male' or 'female'.")
-
-    lang_voices = VOICES[req.language]
-    if req.gender not in lang_voices:
-        gender = list(lang_voices.keys())[0]
-    else:
-        gender = req.gender
-
-    voice = lang_voices[gender]
-    output_path = os.path.join("tts_outputs", f"{uuid.uuid4()}.mp3")
-
-    try:
-        communicate = edge_tts.Communicate(text, voice, rate=req.rate)
-        await communicate.save(output_path)
-    except Exception as e:
-        raise HTTPException(status_code=500, detail=str(e))
-
-    return FileResponse(
-        path=output_path,
-        media_type="audio/mpeg",
-        filename="output.mp3",
-        headers={"X-Voice": voice}
-    )
-
-@app.get("/voices")
-def get_voices():
+import os
+import uuid
+import unicodedata
+import re
+from fastapi import FastAPI, HTTPException, UploadFile, File, Form
+from fastapi.responses import FileResponse
+from pydantic import BaseModel
+import edge_tts
+
+app = FastAPI(title="Edge TTS API", description="Microsoft Edge Neural TTS API")
+
+os.makedirs("tts_outputs", exist_ok=True)
+
+VOICES = {
+    "ar": {"male": "ar-EG-ShakirNeural", "female": "ar-EG-SalmaNeural"},
+    "ar-sa": {"female": "ar-SA-ZariyahNeural"},
+    "en": {"male": "en-US-GuyNeural", "female": "en-US-AvaNeural"},
+    "en-gb": {"female": "en-GB-SoniaNeural"},
+    "fr": {"male": "fr-FR-HenriNeural", "female": "fr-FR-DeniseNeural"},
+    "de": {"male": "de-DE-ConradNeural", "female": "de-DE-KatjaNeural"},
+    "es": {"male": "es-ES-AlvaroNeural", "female": "es-ES-ElviraNeural"},
+    "it": {"male": "it-IT-DiegoNeural", "female": "it-IT-ElsaNeural"},
+    "tr": {"male": "tr-TR-AhmetNeural", "female": "tr-TR-EmelNeural"},
+    "ru": {"male": "ru-RU-DmitryNeural", "female": "ru-RU-SvetlanaNeural"},
+    "hi": {"male": "hi-IN-MadhurNeural", "female": "hi-IN-SwaraNeural"}
+}
+
+SUPPORTED_LANGUAGES = list(VOICES.keys())
+
+def clean_text(text: str) -> str:
+    # Normalize unicode (handles tashkeel and special chars)
+    text = unicodedata.normalize("NFC", text)
+    # Remove control characters except newlines and tabs
+    text = re.sub(r'[\x00-\x08\x0b\x0c\x0e-\x1f\x7f]', '', text)
+    # Replace multiple newlines/spaces with single space
+    text = re.sub(r'\s+', ' ', text)
+    return text.strip()
+
+class TTSRequest(BaseModel):
+    text: str
+    language: str = "en"
+    gender: str = "female"
+    rate: str = "+0%"
+
+@app.get("/")
+def root():
+    return {"message": "Edge TTS API is running ✅"}
+
+@app.post("/tts")
+async def synthesize(req: TTSRequest):
+    text = clean_text(req.text)
+
+    if not text:
+        raise HTTPException(status_code=400, detail="Text cannot be empty.")
+    if req.language not in VOICES:
+        raise HTTPException(status_code=400, detail=f"Unsupported language. Choose from: {SUPPORTED_LANGUAGES}")
+    if req.gender not in ["male", "female"]:
+        raise HTTPException(status_code=400, detail="Gender must be 'male' or 'female'.")
+
+    lang_voices = VOICES[req.language]
+    gender = req.gender if req.gender in lang_voices else list(lang_voices.keys())[0]
+    voice = lang_voices[gender]
+
+    output_path = os.path.join("tts_outputs", f"{uuid.uuid4()}.mp3")
+
+    try:
+        communicate = edge_tts.Communicate(text, voice, rate=req.rate)
+        await communicate.save(output_path)
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+    return FileResponse(
+        path=output_path,
+        media_type="audio/mpeg",
+        filename="output.mp3",
+        headers={"X-Voice": voice}
+    )
+
+@app.get("/voices")
+def get_voices():
     return VOICES