diff --git a/CLAUDE.md b/CLAUDE.md
index a807b8a..a7ddf18 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -8,12 +8,12 @@
 **CRITICAL: Always use consistent naming across all files.**
 
 ### Project Name
-- ✅ **Correct:** `uncloseai-speech` (lowercase, hyphenated)
-- ❌ **Wrong:** "UncloseAI Speech", "Uncloseai Speech", "UncloseAI-Speech"
+- **Correct:** `uncloseai-speech` (lowercase, hyphenated)
+- **Wrong:** "UncloseAI Speech", "Uncloseai Speech", "UncloseAI-Speech"
 
 ### Organization Name
-- ✅ **Correct:** `uncloseai` (lowercase, one word)
-- ❌ **Wrong:** "UncloseAI", "Unclose AI", "UnClose AI"
+- **Correct:** `uncloseai` (lowercase, one word)
+- **Wrong:** "UncloseAI", "Unclose AI", "UnClose AI"
 
 ### Usage Guidelines
 - **In code:** Use `uncloseai-speech` for project references
@@ -23,204 +23,101 @@
 - **Docker images:** `uncloseai-speech` (lowercase, hyphenated)
 - **API responses:** Use `"owned_by": "uncloseai"` (lowercase, one word)
 
-### Examples
-```python
-# Correct
-description='uncloseai-speech API Server'
-owned_by = "uncloseai"
-
-# Wrong
-description='UncloseAI Speech API Server'
-owned_by = "UncloseAI"
-```
-
-```markdown
-# Correct
-# uncloseai-speech
-
-**Raccoon Mission:** Rescue abandoned TTS models and integrate them into uncloseai-speech
-
-# Wrong
-# UncloseAI Speech
-
-**Raccoon Mission:** Rescue abandoned TTS models and integrate them into UncloseAI Speech
-```
-
 ## Core Principles
 
 ### 1. Makefile-First Development
 
 **ALWAYS prefer Makefile targets over manual commands.**
 
-- ✅ DO: `make deploy`, `make voices`, `make test`
-- ❌ DON'T: Manual ssh commands, docker commands, curl commands
-
-**When adding new functionality:**
-1. Add it to the Makefile first
-2. Document it in `make help`
-3. Test it works from scratch
-4. Only then modify other files if needed
+- DO: `make deploy`, `make voices`, `make test`
+- DON'T: Manual docker commands, curl commands
 
 **Makefile is the source of truth** for all deployment and development tasks.
 
-### 2. Work Locally, Deploy Remotely
+### 2. Remote Access: tmux-hosts and tmux ONLY
 
-- **Local development:** `/home/fox/git/uncloseai-speech/`
-- **Remote server:** `ai.foxhop.net` (configured in `vars.sh`, gitignored)
-- **Never create remote directories manually** - let Makefile handle it
-- **Always test from scratch** - `make clean` then `make deploy`
+**CRITICAL: NEVER use ssh, scp, or rsync to access remote servers.**
 
-### 3. Configuration Management
+Use `tmux-hosts` to discover tmux windows, then `tmux send-keys` to run commands.
+
+```bash
+# Discover available hosts
+tmux-hosts
+# Output:
+# 0:0          ai.foxhop.net
+# 0:1          3090-ai.foxhop.net
+
+# Run a command on 3090-ai
+tmux send-keys -t 0:1 'command here' Enter
+
+# Read output
+tmux capture-pane -t 0:1 -p | tail -20
+```
+
+- **NEVER** use `ssh user@host "command"` -- use `tmux send-keys -t 0:1`
+- **NEVER** use `rsync` or `scp` -- use `git push` then `tmux send-keys -t 0:1 'git pull' Enter`
+- **ALWAYS** discover the correct window with `tmux-hosts` first
+
+### 3. Git-Based Deployment
+
+**We use git, not rsync/scp.** All code syncs via git push/pull.
+
+```bash
+# Deploy workflow:
+# 1. Commit and push locally
+git add files && git commit -m "message" && git push
+
+# 2. Pull and rebuild on server via tmux
+tmux send-keys -t 0:1 'cd ~/git/uncloseai-speech && git pull && sudo docker compose up -d --build' Enter
+```
+
+### 4. All Commands Run Locally
+
+The Makefile assumes it runs on the server directly. No remote execution.
+When you need to run make targets on the server, use tmux:
+
+```bash
+tmux send-keys -t 0:1 'cd ~/git/uncloseai-speech && make deploy' Enter
+```
+
+### 5. Configuration Management
 
-- `vars.sh` - Deployment secrets (gitignored, never commit)
-- `vars.sh.example` - Template for users (commit this)
 - `sample.env` - Default environment (commit this)
-- `speech.env` - Runtime environment (created automatically by Makefile)
+- `speech.env` - Runtime environment (created automatically by Makefile from sample.env)
 
-**Key environment variables:**
-- `WORKERS` - Number of uvicorn workers (default: 1 for GPU models like Qwen3-TTS)
-  - Use 1 for GPU-bound models to avoid VRAM duplication across workers
-  - Increase for CPU-bound models like Piper (e.g., WORKERS=4)
-
-**Never view or log secrets** - source them and use them.
-
-### 4. Git Commit Guidelines
+### 6. Git Commit Guidelines
 
 - **Never add AI attribution** - Do not use `Co-Authored-By: Claude` or similar in commit messages
 - Write clear, concise commit messages describing what changed and why
 - Use imperative mood ("Add feature" not "Added feature")
 
-### 5. Documentation Requirements
-
-When adding features, update ALL relevant docs:
-- `Makefile` help text
-- `docs/MODELS.md` for new TTS engines
-- `docs/MIRRORS.md` for binary downloads
-- `docs/AUDIT.md` for file changes
-- This file (`docs/CLAUDE.md`) for new patterns
-
-## Common Tasks
-
-### Full Deployment from Scratch
-
-```bash
-# 1. Clean everything
-make clean
-
-# 2. Deploy (commit, push, pull on server, rebuild container)
-git push && tmux send-keys -t 0:1 'cd ~/uncloseai-speech && git pull && sudo docker-compose up --build -d' Enter
-
-# 3. Download voices (Piper + XTTS samples)
-make voices
-
-# 4. Test
-make test
-make test-xtts
-```
-
-### Adding a New TTS Engine
-
-1. Document it in `docs/MODELS.md` first
-2. Add download target to Makefile (e.g., `voices-silero`)
-3. Implement engine wrapper in `speech.py` or `src/engines/`
-4. Add test target (e.g., `test-silero`)
-5. Update `make voices` to include it
-6. Test full cycle: commit, push, pull on server, rebuild, test
-
-### Debugging Issues
-
-```bash
-make logs          # Tail live logs
-make logs | grep ERROR  # Filter errors
-```
-
-Never use raw docker/ssh commands - extend Makefile if needed.
-
-## File Organization
-
-### Scripts vs Docs
-
-- `scripts/` - Executable utilities (add_voice.py, download_samples.sh, etc.)
-- `docs/` - Documentation ONLY (no executable code)
-- Dockerfiles, startup.sh - Root level (build artifacts)
-- Makefile - Root level (primary interface)
-
-**Never put executable scripts in docs/ directory.**
-
-### Current Structure (as of 2025-11-09)
-
-```
-uncloseai-speech/
-├── Makefile              # PRIMARY INTERFACE - always update first
-├── vars.sh               # Secrets (gitignored)
-├── vars.sh.example       # Template
-├── speech.py             # Main server (will refactor to src/)
-├── openedai.py           # API models
-├── voice_to_speaker.default.yaml  # Voice config
-├── docs/
-│   ├── CLAUDE.md         # This file
-│   ├── AUDIT.md          # Repository audit
-│   ├── MODELS.md         # TTS engines
-│   └── MIRRORS.md        # Binary mirror strategy
-├── scripts/
-│   ├── add_voice.py
-│   ├── say.py
-│   ├── test_voices.sh
-│   └── download_samples.sh
-├── Dockerfile
-├── docker-compose.yml
-└── startup.sh
-```
-
-## TTS Engine Status
-
-### Default Model (Qwen3-TTS)
-- ✅ **Qwen3-TTS (tts-1-qwen)** - DEFAULT - 1.7B params, 10 languages, voice cloning, 97ms latency
-
-### Other Engines (disabled by default, enable in voice_to_speaker.yaml)
-- Piper TTS (tts-1) - 55 voices, fast CPU inference
-- XTTS v2 (tts-1-hd) - Voice cloning, multilingual
-- Silero TTS (tts-1-silero) - 142 voices, 5 languages, auto-downloads
-- Kokoro TTS (tts-1-kokoro) - 32 voices, lightweight (82M params)
-
-### Why Qwen3-TTS is Default
-- State-of-the-art quality with voice cloning
-- Actively maintained by Alibaba
-- Apache 2.0 license (commercial-friendly)
-- 10 languages: Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian
-- Fast first-packet latency (97ms)
-- Easy voice cloning from 3-second samples
-
-See `docs/MODELS.md` for complete roadmap and detailed model documentation.
-
 ## Production Deployment
 
-**Production Server:** `3090-ai.foxhop.net`
-- **URL:** https://speech.ai.unturf.com (proxied via ai.foxhop.net)
-- **Repo Location:** `/home/fox/uncloseai-speech`
-- **Container:** `uncloseai-speech_server_1` (image: `uncloseai-speech:local`)
-- **tmux access:** Use `tmux-hosts` to discover window mappings, then `tmux send-keys -t 0:1 'command' Enter`
-- **Current mapping:** window `0:1` is `3090-ai.foxhop.net` (verify with `tmux-hosts`)
+**Production Server:** `3090-ai.foxhop.net` (tmux window `0:1`)
+- **URL:** https://speech.ai.unturf.com
+- **Repo Location:** `/home/fox/git/uncloseai-speech`
+- **Container:** `uncloseai-speech-server-1`
+- **Git remote:** `ssh://git@git.unturf.com:2222/engineering/unturf/uncloseai-speech.git`
+- **Git user on server:** `timehexon <timehexon@unturf.com>`
 
 ### Deployment Workflow
 
-**We use git, not rsync.** Commit locally, push, pull on server, rebuild.
-
 ```
 Local:
   /home/fox/git/uncloseai-speech/
 
-  ↓ git commit && git push
+  git commit && git push
 
-Remote (3090-ai.foxhop.net):
-  /home/fox/uncloseai-speech/
+Remote (3090-ai, tmux 0:1):
+  /home/fox/git/uncloseai-speech/
 
-  ↓ git pull && sudo docker-compose up --build -d
+  git pull && sudo docker compose up -d --build
 
 Container:
   /app/
   ├── speech.py
-  ├── voices/samples/  (cloned-voices mounted)
+  ├── cloned-voices/     (mounted from host)
+  ├── voices/            (mounted from host)
   └── config/
       └── voice_to_speaker.yaml
 ```
@@ -228,122 +125,100 @@ Container:
 ### Quick Production Commands
 
 ```bash
-# Use tmux-hosts to see available tmux windows
+# Discover tmux windows
 tmux-hosts
 
-# Push changes and deploy
-git add -A && git commit -m "message" && git push
-tmux send-keys -t 0:1 'cd ~/uncloseai-speech && git pull && sudo docker-compose up --build -d' Enter
+# Deploy changes
+git push
+tmux send-keys -t 0:1 'cd ~/git/uncloseai-speech && git pull && sudo docker compose up -d --build' Enter
 
 # Check container status
 tmux send-keys -t 0:1 'sudo docker ps | grep speech' Enter
 
 # View logs
-tmux send-keys -t 0:1 'sudo docker logs --tail 50 uncloseai-speech_server_1' Enter
+tmux send-keys -t 0:1 'sudo docker logs --tail 50 uncloseai-speech-server-1' Enter
 
 # Restart container
-tmux send-keys -t 0:1 'cd ~/uncloseai-speech && sudo docker-compose restart' Enter
+tmux send-keys -t 0:1 'cd ~/git/uncloseai-speech && sudo docker compose restart' Enter
+
+# Read output from tmux
+tmux capture-pane -t 0:1 -p | tail -20
 ```
 
-## Testing Philosophy
+## Voice Configuration
 
-**Full stack testing workflow:**
-1. Commit and push changes
-2. Pull on server and rebuild: `git pull && sudo docker-compose up --build -d`
-3. Wait for model to load (check logs)
-4. Test via curl or browser
+21 distinct gendered voices from LibriSpeech test-clean (public domain):
+- **Female (11):** aria, clara, elena, grace, hazel, iris, luna, maya, ruby, sage, sofia
+- **Male (10):** atlas, caleb, felix, hugo, jasper, kai, leo, marcus, owen, theo
 
-**Never assume** - always test from scratch after changes.
+Voice WAV files are in `cloned-voices/`, mounted into the container.
+Config is in `voice_to_speaker.default.yaml`.
 
-## Raccoon Mission Values
+## TTS Engine Status
 
-1. **Resilience** - Assume upstream dies, plan mirrors
-2. **Simplicity** - Makefile > manual commands
-3. **Documentation** - Write docs before code
-4. **Liberation** - Keep TTS libre (AGPL v3)
-5. **Unification** - All TTS engines, one API
+### Default Model (Qwen3-TTS)
+- **Qwen3-TTS (tts-1-qwen)** - DEFAULT - 1.7B params, 10 languages, voice cloning
 
-## AGPL v3 Compliance
+### Other Engines (disabled by default, enable in voice_to_speaker.yaml)
+- Piper TTS (tts-1) - 55 voices, fast CPU inference
+- XTTS v2 (tts-1-hd) - Voice cloning, multilingual
+- Silero TTS (tts-1-silero) - 142 voices, 5 languages, auto-downloads
+- Kokoro TTS (tts-1-kokoro) - 32 voices, lightweight (82M params)
 
-**This project is AGPL v3 licensed.** The key obligation: anyone who uses this TTS service over a network must be able to access the source code.
+See `docs/MODELS.md` for complete roadmap.
 
-### What This Means
+## Testing
 
-Unlike regular GPL, AGPL closes the "SaaS loophole". If you run uncloseai-speech as a service (even without distributing binaries), users have the right to request source code.
+```bash
+# Run on server via tmux
+tmux send-keys -t 0:1 'cd ~/git/uncloseai-speech && make test' Enter
 
-### Requirements for Operators
-
-When running uncloseai-speech as a network service, you must provide:
-- Complete source code of the running version
-- Any modifications you've made
-- Build instructions
-
-### How to Comply
-
-1. **Link in API response** - Add source URL to `/v1/models` or root endpoint
-2. **Link in documentation** - Include repository URL in service docs
-3. **Host source code** - Keep your fork in a public git repository
-
-### Example Implementation
-
-```python
-# In API responses
-"source_code": "https://github.com/uncloseai/uncloseai-speech"
+# Or test from any machine with curl
+curl -X POST http://3090-ai.foxhop.net:8000/v1/audio/speech \
+  -H "Content-Type: application/json" \
+  -d '{"model":"tts-1-qwen","voice":"aria","input":"Test"}' \
+  -o /tmp/test.mp3
 ```
 
-### Why AGPL?
-
-- Ensures forks remain open source
-- Community improvements flow back to the project
-- Prevents proprietary TTS services from using our work without sharing back
-- Aligns with Raccoon Mission: **Keep TTS libre**
-
-## Common Mistakes to Avoid
-
-❌ DON'T create directories with raw ssh
-✅ DO add Makefile target for deployment
-
-❌ DON'T use rsync - we use git
-✅ DO commit, push, pull on server, then rebuild with docker-compose
-
-❌ DON'T put scripts in docs/
-✅ DO put scripts in scripts/, reference from docs
-
-❌ DON'T hardcode paths/hosts
-✅ DO use vars.sh variables
-
-❌ DON'T forget to commit and push before deploying
-✅ DO commit, push, pull on server, rebuild container
-
 ## When Things Break
 
-1. Check logs: `tmux send-keys -t 0:1 'sudo docker logs --tail 50 uncloseai-speech_server_1' Enter`
-2. Check GPU memory: `tmux send-keys -t 0:1 'nvidia-smi' Enter`
-3. Restart container: `tmux send-keys -t 0:1 'sudo docker-compose restart' Enter`
-4. Rebuild: `git pull && sudo docker-compose up --build -d`
-5. Check voice files: `tmux send-keys -t 0:1 'ls voices/samples/' Enter`
+```bash
+# Check logs
+tmux send-keys -t 0:1 'sudo docker logs --tail 50 uncloseai-speech-server-1' Enter
 
-## Multiprocess Architecture (uvicorn workers=4)
+# Check GPU memory
+tmux send-keys -t 0:1 'nvidia-smi' Enter
 
-**Key pattern:** Worker processes spawn as fresh imports, don't run `__main__` block.
+# Restart container
+tmux send-keys -t 0:1 'cd ~/git/uncloseai-speech && sudo docker compose restart' Enter
 
-**Solutions implemented:**
+# Full rebuild
+tmux send-keys -t 0:1 'cd ~/git/uncloseai-speech && git pull && sudo docker compose up -d --build' Enter
+
+# Read tmux output
+tmux capture-pane -t 0:1 -p | tail -20
+```
+
+## Common Mistakes to Avoid
+
+- DON'T use `ssh user@host "command"` -- use `tmux send-keys -t 0:1`
+- DON'T use `rsync` or `scp` -- use `git push` + `tmux send-keys -t 0:1 'git pull' Enter`
+- DON'T hardcode tmux window numbers -- use `tmux-hosts` to discover them
+- DON'T put scripts in docs/ -- put them in scripts/
+- DON'T forget to push before deploying
+
+## AGPL v3 Compliance
+
+**This project is AGPL v3 licensed.** Anyone using this TTS service over a network must be able to access the source code.
+
+## Multiprocess Architecture
+
+Worker processes spawn as fresh imports, don't run `__main__` block.
 1. **Caches** - Initialize in `lifespan` context manager (runs per worker)
 2. **Args** - Use `DefaultArgs` class at module level, override in `__main__`
 
 See `speech.py:23-113` for implementation.
 
-## Future Refactoring (Planned)
-
-- Move `speech.py`, `openedai.py`, `audio_reader.py` → `src/`
-- Create engine abstraction layer in `src/engines/`
-- Unified voice config with engine selection
-- Binary mirror implementation (MinIO on ai.foxhop.net)
-
-See `docs/AUDIT.md` for detailed refactoring plan.
-
 ---
 
-**Remember:** Makefile first, documentation second, code third. Test from scratch every time.
-
-🦝 **Raccoon Mission:** Keep TTS libre, rescue abandoned models, unify all engines.
+**Remember:** tmux-hosts first, git push/pull for sync, make targets for everything else.