Restore Kokoro files

Dockerfile

@@ -1,5 +1,19 @@
-FROM python:3.11-slim
+# Use a more complete base image
+FROM python:3.11
+
 WORKDIR /app
-COPY test_build.py .
-RUN pip install fastapi uvicorn
-CMD ["uvicorn", "test_build:app", "--host", "0.0.0.0", "--port", "7860"]
+
+# System deps - use a single RUN to avoid cache issues
+RUN apt-get update && apt-get install -y espeak-ng libespeak-ng1 && rm -rf /var/lib/apt/lists/*
+
+# Python deps
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# App
+COPY main.py .
+
+ENV PORT=7860
+EXPOSE 7860
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

Dockerfile.kokoro

@@ -1,19 +0,0 @@
-# Use a more complete base image
-FROM python:3.11
-
-WORKDIR /app
-
-# System deps - use a single RUN to avoid cache issues
-RUN apt-get update && apt-get install -y espeak-ng libespeak-ng1 && rm -rf /var/lib/apt/lists/*
-
-# Python deps
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
-
-# App
-COPY main.py .
-
-ENV PORT=7860
-EXPOSE 7860
-
-CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

Dockerfile.test

@@ -0,0 +1,5 @@
+FROM python:3.11-slim
+WORKDIR /app
+COPY test_build.py .
+RUN pip install fastapi uvicorn
+CMD ["uvicorn", "test_build:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -1,5 +1,140 @@
-from fastapi import FastAPI
-app = FastAPI()
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from kokoro_onnx import Kokoro
+import soundfile as sf
+import uuid
+from fastapi.responses import Response
+from io import BytesIO
+from pathlib import Path
+import requests
+import os
+
+app = FastAPI(title="Kokoro 82M TTS API")
+
+# Model files (downloaded on first run, cached in /tmp)
+MODEL_DIR = Path("/tmp/kokoro_models")
+MODEL_DIR.mkdir(exist_ok=True)
+
+MODEL_PATH = MODEL_DIR / "kokoro-v1.0.onnx"
+VOICES_PATH = MODEL_DIR / "voices-v1.0.bin"
+
+MODEL_URL = "https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/kokoro-v1.0.onnx"
+VOICES_URL = "https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/voices-v1.0.bin"
+
+kokoro: Kokoro | None = None
+
+
+def download_file(url: str, dest: Path):
+    """Download file with progress, follow redirects."""
+    if dest.exists():
+        return
+    print(f"Downloading {dest.name}...")
+    with requests.get(url, stream=True, timeout=120, allow_redirects=True) as r:
+        r.raise_for_status()
+        with open(dest, "wb") as f:
+            for chunk in r.iter_content(chunk_size=8192):
+                f.write(chunk)
+    print(f"✓ Downloaded {dest.name}")
+
+
+def get_kokoro() -> Kokoro:
+    global kokoro
+    if kokoro is not None:
+        return kokoro
+
+    # Download model files if needed
+    download_file(MODEL_URL, MODEL_PATH)
+    download_file(VOICES_URL, VOICES_PATH)
+
+    kokoro = Kokoro(str(MODEL_PATH), str(VOICES_PATH))
+    print(f"✓ Kokoro loaded. Available voices: {len(kokoro.get_voices())}")
+    return kokoro
+
+
+# Warm up on startup
+@app.on_event("startup")
+async def warmup():
+    try:
+        get_kokoro()
+        print("Warmup complete")
+    except Exception as e:
+        print(f"Warmup failed (will retry on first request): {e}")
+
+
+class TTSRequest(BaseModel):
+    text: str
+    voice: str = "af_heart"  # Default voice (US female)
+    speed: float = 1.0       # Speed multiplier
+    sample_rate: int = 24000  # Kokoro outputs 24kHz
+
+
+@app.post("/tts")
+async def tts(request: TTSRequest):
+    k = get_kokoro()
+
+    # Validate voice
+    available = k.get_voices()
+    if request.voice not in available:
+        raise HTTPException(
+            400,
+            f"Voice '{request.voice}' not available. Available: {available[:20]}... (total {len(available)})",
+        )
+
+    try:
+        # Generate audio (returns numpy array at 24kHz)
+        audio, sr = k.create(
+            request.text,
+            voice=request.voice,
+            speed=request.speed,
+            lang="en-us",  # Kokoro uses lang code for G2P
+        )
+
+        # Resample if requested sample_rate differs (simple approach: just return 24kHz)
+        # For proper resampling, add scipy/samplerate. Keeping it simple: return native 24kHz.
+        buffer = BytesIO()
+        sf.write(buffer, audio, sr, format="WAV", subtype="PCM_16")
+        buffer.seek(0)
+
+        return Response(
+            content=buffer.read(),
+            media_type="audio/wav",
+            headers={"Content-Disposition": f"attachment; filename=tts_{uuid.uuid4().hex}.wav"},
+        )
+    except Exception as e:
+        raise HTTPException(500, f"Synthesis failed: {str(e)}")
+
+
+@app.get("/health")
+async def health():
+    k = get_kokoro()
+    return {
+        "status": "healthy",
+        "model": "kokoro-v1.0",
+        "sample_rate": 24000,
+        "voices_count": len(k.get_voices()),
+        "voices_preview": k.get_voices()[:10],
+    }
+
+
 @app.get("/")
-def root():
-    return {"message": "test"}
+async def root():
+    k = get_kokoro()
+    return {
+        "message": "Kokoro 82M TTS API - High quality CPU TTS",
+        "model": "kokoro-v1.0 (82M params, Apache 2.0)",
+        "sample_rate": 24000,
+        "endpoint": "/tts (POST)",
+        "voices_total": len(k.get_voices()),
+        "example": {
+            "text": "Hello, this is Kokoro 82M text to speech!",
+            "voice": "af_heart",
+            "speed": 1.0,
+        },
+        "voice_categories": {
+            "us_female": [v for v in k.get_voices() if v.startswith("af_")],
+            "us_male": [v for v in k.get_voices() if v.startswith("am_")],
+            "uk_female": [v for v in k.get_voices() if v.startswith("bf_")],
+            "uk_male": [v for v in k.get_voices() if v.startswith("bm_")],
+            "other": [v for v in k.get_voices() if not v.startswith(("af_", "am_", "bf_", "bm_"))],
+        },
+    }

main.py.kokoro

@@ -1,140 +0,0 @@
-from fastapi import FastAPI, HTTPException
-from pydantic import BaseModel
-from kokoro_onnx import Kokoro
-import soundfile as sf
-import uuid
-from fastapi.responses import Response
-from io import BytesIO
-from pathlib import Path
-import requests
-import os
-
-app = FastAPI(title="Kokoro 82M TTS API")
-
-# Model files (downloaded on first run, cached in /tmp)
-MODEL_DIR = Path("/tmp/kokoro_models")
-MODEL_DIR.mkdir(exist_ok=True)
-
-MODEL_PATH = MODEL_DIR / "kokoro-v1.0.onnx"
-VOICES_PATH = MODEL_DIR / "voices-v1.0.bin"
-
-MODEL_URL = "https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/kokoro-v1.0.onnx"
-VOICES_URL = "https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/voices-v1.0.bin"
-
-kokoro: Kokoro | None = None
-
-
-def download_file(url: str, dest: Path):
-    """Download file with progress, follow redirects."""
-    if dest.exists():
-        return
-    print(f"Downloading {dest.name}...")
-    with requests.get(url, stream=True, timeout=120, allow_redirects=True) as r:
-        r.raise_for_status()
-        with open(dest, "wb") as f:
-            for chunk in r.iter_content(chunk_size=8192):
-                f.write(chunk)
-    print(f"✓ Downloaded {dest.name}")
-
-
-def get_kokoro() -> Kokoro:
-    global kokoro
-    if kokoro is not None:
-        return kokoro
-
-    # Download model files if needed
-    download_file(MODEL_URL, MODEL_PATH)
-    download_file(VOICES_URL, VOICES_PATH)
-
-    kokoro = Kokoro(str(MODEL_PATH), str(VOICES_PATH))
-    print(f"✓ Kokoro loaded. Available voices: {len(kokoro.get_voices())}")
-    return kokoro
-
-
-# Warm up on startup
-@app.on_event("startup")
-async def warmup():
-    try:
-        get_kokoro()
-        print("Warmup complete")
-    except Exception as e:
-        print(f"Warmup failed (will retry on first request): {e}")
-
-
-class TTSRequest(BaseModel):
-    text: str
-    voice: str = "af_heart"  # Default voice (US female)
-    speed: float = 1.0       # Speed multiplier
-    sample_rate: int = 24000  # Kokoro outputs 24kHz
-
-
-@app.post("/tts")
-async def tts(request: TTSRequest):
-    k = get_kokoro()
-
-    # Validate voice
-    available = k.get_voices()
-    if request.voice not in available:
-        raise HTTPException(
-            400,
-            f"Voice '{request.voice}' not available. Available: {available[:20]}... (total {len(available)})",
-        )
-
-    try:
-        # Generate audio (returns numpy array at 24kHz)
-        audio, sr = k.create(
-            request.text,
-            voice=request.voice,
-            speed=request.speed,
-            lang="en-us",  # Kokoro uses lang code for G2P
-        )
-
-        # Resample if requested sample_rate differs (simple approach: just return 24kHz)
-        # For proper resampling, add scipy/samplerate. Keeping it simple: return native 24kHz.
-        buffer = BytesIO()
-        sf.write(buffer, audio, sr, format="WAV", subtype="PCM_16")
-        buffer.seek(0)
-
-        return Response(
-            content=buffer.read(),
-            media_type="audio/wav",
-            headers={"Content-Disposition": f"attachment; filename=tts_{uuid.uuid4().hex}.wav"},
-        )
-    except Exception as e:
-        raise HTTPException(500, f"Synthesis failed: {str(e)}")
-
-
-@app.get("/health")
-async def health():
-    k = get_kokoro()
-    return {
-        "status": "healthy",
-        "model": "kokoro-v1.0",
-        "sample_rate": 24000,
-        "voices_count": len(k.get_voices()),
-        "voices_preview": k.get_voices()[:10],
-    }
-
-
-@app.get("/")
-async def root():
-    k = get_kokoro()
-    return {
-        "message": "Kokoro 82M TTS API - High quality CPU TTS",
-        "model": "kokoro-v1.0 (82M params, Apache 2.0)",
-        "sample_rate": 24000,
-        "endpoint": "/tts (POST)",
-        "voices_total": len(k.get_voices()),
-        "example": {
-            "text": "Hello, this is Kokoro 82M text to speech!",
-            "voice": "af_heart",
-            "speed": 1.0,
-        },
-        "voice_categories": {
-            "us_female": [v for v in k.get_voices() if v.startswith("af_")],
-            "us_male": [v for v in k.get_voices() if v.startswith("am_")],
-            "uk_female": [v for v in k.get_voices() if v.startswith("bf_")],
-            "uk_male": [v for v in k.get_voices() if v.startswith("bm_")],
-            "other": [v for v in k.get_voices() if not v.startswith(("af_", "am_", "bf_", "bm_"))],
-        },
-    }

test_main.py

@@ -0,0 +1,5 @@
+from fastapi import FastAPI
+app = FastAPI()
+@app.get("/")
+def root():
+    return {"message": "test"}