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

pipecat-agent/requirements.txt

@@ -1,12 +1,7 @@
 pipecat-ai[livekit,silero,openai]==0.0.48
-fastapi==0.115.0
-uvicorn[standard]==0.30.0
-anthropic==0.34.0
-faster-whisper==1.0.3
-requests==2.32.3
 httpx==0.27.0
 python-dotenv==1.0.1
 structlog==24.4.0
-numpy==1.26.4
-soundfile==0.12.1
 livekit-api==0.7.1
+fastapi==0.115.0
+uvicorn[standard]==0.30.0