feat: design model support for qwen-tts backend. remove unnecessary port split for qwen models

1 files changed, 21 insertions, 4 deletions

diff --git a/app/docs/backend-qwen.md b/app/docs/backend-qwen.md
index d0e7c92..5cfb0b3 100644
--- a/app/docs/backend-qwen.md
+++ b/app/docs/backend-qwen.md
@@ -1,8 +1,10 @@
 # Backend Option 2: Qwen3-TTS
 
-The easiest way is to run `python audiobook.py` → **Configure backends… → Install Backend → qwen-tts** (or `python app/backends/qwen.py`): the TUI pip-installs `qwen-tts` into its managed venv (`app/envs/tts`) — that's all there is to it, the install asks no questions. The two demo ports live in `app/converter/config.py` (edit them in the hub's **Settings** screen), and you pick the built-in speaker per run on the **Generate audiobooks** screen (it defaults to `SPEAKER` in `app/converter/config.py`). You can also start the server from the hub's **Start/Stop Backend Servers** menu, or let a conversion start it automatically.
+The easiest way is to run `python audiobook.py` → **Configure backends… → Install Backend → qwen-tts** (or `python app/backends/qwen.py`): the TUI pip-installs `qwen-tts` into its managed venv (`app/envs/tts`) — that's all there is to it, the install asks no questions. The demo port lives in `app/converter/config.py` (edit it in the hub's **Settings** screen). The qwen backend runs **one model at a time** on that single port: pick Base, CustomVoice or VoiceDesign per run on the **Generate audiobooks** screen (the choice is remembered in `QWEN_MODEL` and re-used by the next autostart; switching models while a managed server is up restarts it with the newly-selected model). You can also start the server from the hub's **Start/Stop Backend Servers** menu, or let a conversion start it automatically.
 
-If you prefer to install the backend yourself (in your own environment, not the managed venv), the manual steps are below. Either way the hub detects a running server by its port, so a manually-installed backend works once its server is up. To use demo servers on another machine, set `QWEN_REMOTE_URL`/`CLONE_REMOTE_URL` in `app/converter/config.py` to their `host:port` (defaults `127.0.0.1:7860`/`:7861`) — the hub probes each and offers the matching `qwen-tts [remote]` mode — or pass `--api-url` on the CLI.
+If you prefer to install the backend yourself (in your own environment, not the managed venv), the manual steps are below. Either way the hub detects a running server by its port (its `GET /info` names which of the three demos answers), so a manually-installed backend works once its server is up. To use a demo server on another machine, set `QWEN_REMOTE_URL` in `app/converter/config.py` to its `host:port` (default `127.0.0.1:7860`) — the hub probes it and offers the matching `qwen-tts [remote]` mode limited to the model that server hosts — or pass `--api-url` on the CLI.
+
+Model weights download automatically from HuggingFace into the standard cache (`~/.cache/huggingface/hub`) the first time a server for each model starts — there is nothing else to install per model.
 
 Install qwen-tts with pip into your environment:
 
@@ -12,12 +14,27 @@ source audiobook/bin/activate
 pip install -U qwen-tts
 ```
 
-Run the backend with `qwen-tts-demo`. Add `--no-flash-attn` if FlashAttention isn't installed (see below). Note that the Base model and CustomVoice model run on different ports.
+Run the backend with `qwen-tts-demo <model>`. Add `--no-flash-attn` if FlashAttention isn't installed (see below).
+
+## Voice design
+
+```bash
+qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign --ip 127.0.0.1 --port 7860 [--no-flash-attn]
+```
+
+Then:
+
+```bash
+python audiobook.py --backend qwen \
+    --instructions "A warm adult female narrator with a British accent"
+```
+
+The narrator is tagged "designed" in output file names.
 
 ## Voice clone
 
 ```bash
-qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-Base --ip 127.0.0.1 --port 7861 [--no-flash-attn]
+qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-Base --ip 127.0.0.1 --port 7860 [--no-flash-attn]
 ```
 
 Then in another terminal: