feat: VoiceCoach v2 - OpenClaw gateway + Speaches STT/TTS

- pipeline.py: completely rewritten to use Speaches STT/TTS and OpenClaw LLM
- main.py: v2 with OPENCLAW_TOKEN support
- requirements.txt: slimmed (removed anthropic, faster-whisper direct deps)
- Dockerfile: slimmer build (no model pre-download)
- whisper_stt.py, piper_tts.py: removed (replaced by Speaches API)
- docker-compose.yml: v2 with speaches + openclaw services, piper-tts removed
- openclaw-agent/system_prompt.md: new directory with agent system prompt

piper-service/main.py

@@ -35,7 +35,7 @@ app = FastAPI(title="Piper TTS Service", lifespan=lifespan)
 
 class TTSRequest(BaseModel):
     text: str
-    speaker_id: int = 0
+    speaker_id: int = None
     length_scale: float = 1.0
     sentence_silence: float = 0.2
 
@@ -57,13 +57,13 @@ async def synthesize(req: TTSRequest):
 
     buf = io.BytesIO()
     with wave.open(buf, "wb") as wf:
-        voice.synthesize(
-            req.text,
-            wf,
-            speaker_id=req.speaker_id,
-            length_scale=req.length_scale,
-            sentence_silence=req.sentence_silence,
-        )
+        synth_kwargs = {
+            "length_scale": req.length_scale,
+            "sentence_silence": req.sentence_silence,
+        }
+        if req.speaker_id is not None:
+            synth_kwargs["speaker_id"] = req.speaker_id
+        voice.synthesize(req.text, wf, **synth_kwargs)
 
     return Response(
         content=buf.getvalue(),