Funktioniert

test_ws.py

@@ -6,6 +6,7 @@ import time
 import wave
 import struct
 import asyncio
+import re
 
 try:
     import websockets
@@ -18,12 +19,30 @@ except ImportError:
 WS_URL = "ws://localhost:8091/v1/audio/speech/stream"
 OUTPUT_FILE = "test_stream_output.wav"
 SAMPLE_RATE = 24000
+WORD_RE = re.compile(r"\S+\s*")
 
 
-async def stream_tts(text: str, voice: str = "Ryan", language: str = "German"):
+def iter_words(text: str):
+    """Yield complete words, preserving trailing whitespace.
+
+    The WebSocket client must not forward raw LLM tokens such as partial
+    subwords. It buffers to words and lets the server detect sentence ends.
+    """
+    for match in WORD_RE.finditer(text):
+        yield match.group(0)
+
+
+async def stream_tts(
+    text: str,
+    voice: str = "Ryan",
+    language: str = "German",
+    instructions: str = "Eine warme, ruhige deutsche Stimme, klar artikuliert, freundlich und natuerlich.",
+    seed: int = 42,
+):
     print(f"[→] WebSocket connect: {WS_URL}")
     print(f"    text:     {text!r}")
-    print(f"    voice:    {voice}, language: {language}")
+    print(f"    voice:    {voice}, language: {language}, seed: {seed}")
+    print(f"    instruct: {instructions!r}")
 
     pcm_chunks = []
     total_bytes = 0
@@ -32,21 +51,28 @@ async def stream_tts(text: str, voice: str = "Ryan", language: str = "German"):
 
     async with websockets.connect(WS_URL) as ws:
         # Send session config
-        await ws.send(json.dumps({
+        config = {
             "type": "session.config",
             "model": "Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice",
-            "task_type": "CustomVoice",
+            "task_type": "VoiceDesign",
             "voice": voice,
             "language": language,
+            "instructions": instructions,
+            "seed": seed,
             "response_format": "pcm",
             "stream_audio": True,
-        }))
+            "split_granularity": "sentence",
+        }
+        print("[cfg]", json.dumps(config, ensure_ascii=False, sort_keys=True), flush=True)
+        await ws.send(json.dumps(config))
 
-        # Send text
-        await ws.send(json.dumps({
-            "type": "input.text",
-            "text": text,
-        }))
+        # Send word-by-word. Do not split into sentences client-side; the
+        # server still decides when a complete sentence is ready for audio.
+        for word in iter_words(text):
+            await ws.send(json.dumps({
+                "type": "input.text",
+                "text": word,
+            }))
         await ws.send(json.dumps({"type": "input.done"}))
 
         # Receive