From df57cf2733e398473a58d788cd97fea3a618f892 Mon Sep 17 00:00:00 2001
From: historia <historiavg@proton.me>
Date: Sun, 23 Aug 2026 14:01:56 -0400
Subject: feat: tui for make_audiocpp_server_json

---
 audiobook.py | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)

(limited to 'audiobook.py')

diff --git a/audiobook.py b/audiobook.py
index d3a5426..6ad056c 100755
--- a/audiobook.py
+++ b/audiobook.py
@@ -48,6 +48,10 @@ Examples:
   # Use the audio.cpp audiocpp_server with a server-side voice preset
   python audiobook.py --backend audiocpp --voice narrator
 
+  # Use the audio.cpp audiocpp_server with a voice design model (task 'vdes')
+  python audiobook.py --backend audiocpp --model qwen-design \\
+      --instructions "A warm adult female narrator with a British accent"
+
   # Use the Qwen demo server with a custom voice
   python audiobook.py --backend qwen
 
@@ -176,6 +180,35 @@ Examples:
               "auto-select when the server hosts exactly one entry.")
     )
 
+    parser.add_argument(
+        "--instructions",
+        type=str,
+        default=None,
+        metavar="TEXT",
+        help=("Voice design or style instruction sent with every request "
+              "(--backend audiocpp only). Required for voice design models "
+              "(server entries with task 'vdes', e.g. Qwen3-TTS "
+              "VoiceDesign): describe the voice to synthesize with, e.g. "
+              "'A warm adult female narrator with a British accent'. On "
+              "other families it acts as a style/delivery instruction when "
+              "the model supports one and is ignored otherwise. Defaults to "
+              "AUDIOCPP_INSTRUCTIONS in converter/config.py (empty).")
+    )
+
+    parser.add_argument(
+        "--option",
+        action="append",
+        type=str,
+        default=None,
+        metavar="KEY=VALUE",
+        help=("Request option passed through to the audio.cpp model "
+              "(--backend audiocpp only); repeatable. Whatever the hosted "
+              "family supports (emotion, voice_id, speed, speaking_rate, "
+              "temperature, ...) — unsupported keys are ignored by the "
+              "model. See the audio.cpp docs for the model's valid option "
+              "keys, e.g. --option emotion=neutral --option speed=1.1.")
+    )
+
     args = parser.parse_args()
 
     if args.speed <= 0:
@@ -242,6 +275,21 @@ Examples:
         parser.error("--model requires --backend audiocpp; it selects an "
                      "audio.cpp server model entry id")
 
+    if args.instructions is not None and args.backend != BACKEND_AUDIOCPP:
+        parser.error("--instructions requires --backend audiocpp; it is "
+                     "sent as the audio.cpp request's instructions field")
+
+    request_options = {}
+    if args.option:
+        if args.backend != BACKEND_AUDIOCPP:
+            parser.error("--option requires --backend audiocpp; the options "
+                         "are passed through to the audio.cpp model")
+        for item in args.option:
+            key, sep, value = item.partition("=")
+            if not sep or not key.strip():
+                parser.error(f"--option expects KEY=VALUE (got {item!r})")
+            request_options[key.strip()] = value
+
     setup_logging(debug=args.debug)
     setup_directories()
 
@@ -261,6 +309,7 @@ Examples:
         voice_mode=voice_mode,
         voice_clone_ref_audio=args.clone,
         output_format=args.format,
+        instructions=args.instructions,
     )
 
     if not book_files:
@@ -287,6 +336,8 @@ Examples:
             debug=args.debug,
             chunk=args.chunk,
             model_id=args.model,
+            instructions=args.instructions,
+            request_options=request_options,
         )
         converter._book_files = book_files
         converter._planned = planned
-- 
cgit v1.2.3