feature: implement base tts with uv and kokoro

tts/main.py

@@ -0,0 +1,13 @@
+from kokoro import KPipeline
+import soundfile as sf
+import sys
+import json
+
+text = sys.stdin.read()
+
+pipeline = KPipeline(lang_code="a", repo_id="hexgrad/Kokoro-82M")
+generator = pipeline(text, voice="af_heart", speed=1.2)
+
+for i, (gs, ps, audio) in enumerate(generator):
+    print(json.dumps({"file": i, "text": gs}))
+    sf.write(f"{i}.wav", audio, 24000)