v1.0

README.md

@@ -5,21 +5,22 @@ Wake-word activated, Ollama-backed, MCP-enabled voice assistant with audiobook-d
 ## Architecture
 
 ```
-microphone ─▶ VAD / wake word ─▶ STT (faster-whisper)
+microphone ─▶ VAD / wake word ─▶ STT (faster-whisper) + speaker ID (ECAPA)
                                           │
                                           ▼
-                                Ollama LLM (llama3.1:8b) ◀─▶ MCP servers (filesystem, fetch, time, …)
+                 quick commands ◀── Ollama LLM ◀─▶ MCP servers (filesystem, fetch, time, …)
                                           │
                                           ▼
-                                  TTS (XTTS v2, cloned voice)
+                                  TTS (Piper VITS, or F5-TTS cloning)
                                           │
                                           ▼
                                        speaker
 ```
 
 - **STT** — faster-whisper, CUDA float16, default `large-v3`.
-- **TTS** — Coqui XTTS v2 (community fork). Zero-shot cloning plus optional fine-tune from audiobook snippets.
-- **LLM** — local Ollama at `http://localhost:11434`, `llama3.1:8b` (native tool calling).
+- **TTS** — Piper (VITS, ONNX) by default, fine-tunable overnight from audiobook snippets;
+  optional F5-TTS zero-shot cloning (`tts.backend: f5`, non-commercial weights).
+- **LLM** — local Ollama at `http://localhost:11434` (native tool calling).
 - **MCP** — host/client only, reads `mcp_servers.json` (VS Code-compatible).
 - **Wake word** — openWakeWord, default `hey_jarvis` (custom "Javis" model trainable later).
 - **GUI** — PySide6 + qasync.
@@ -27,7 +28,7 @@ microphone ─▶ VAD / wake word ─▶ STT (faster-whisper)
 ## Prerequisites
 
 - Windows 10/11
-- Python 3.10 or 3.11 (XTTS does not yet support 3.12)
+- Python 3.10 or 3.11 (tested on 3.10; `piper-tts` is pinned to the 1.x line)
 - NVIDIA GPU + recent CUDA drivers (CPU works but slow)
 - A running Ollama instance with the chosen model pulled:
   ```powershell
@@ -118,8 +119,8 @@ Javis/
     core/        config, logger, state machine, event bus
     audio_io/    devices, mic stream, VAD, wake word
     stt/         faster-whisper
-    tts/         backend interface, XTTS implementation
-    voices/      profiles, audiobook ingest, fine-tune
+    tts/         backend interface, Piper + F5 implementations
+    voices/      profiles, audiobook ingest, Piper training + scheduler
     llm/         Ollama client, conversation memory
     mcp_client/  host, schema bridge
     agent/       orchestrator, system prompts
@@ -128,4 +129,13 @@ Javis/
 
 ## Status
 
-Initial scaffold. End-to-end voice loop works once dependencies and a voice reference clip are provided.
+End-to-end voice loop works once dependencies and a voice model/reference clip are provided.
+See [docs/AUDIT.md](docs/AUDIT.md) for the latest code audit.
+
+## Tests
+
+```powershell
+pip install -e .[dev]
+python -m pytest tests -q --ignore=tests/_retheme_check.py
+$env:QT_QPA_PLATFORM="offscreen"; python tests\_retheme_check.py   # GUI smoke test
+```