Drop audioop: request 16 kHz directly via Speaches sample_rate extension

Settles the Python version question: floor >=3.11, no ceiling.
Container moves to python:3.13-slim, CI tests on 3.13. The embedded
Piper fallback resamples with numpy (already present via [speech]).
Verified with a live round trip at 16 kHz.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

gateway/src/desklock_gateway/tts.py

@@ -1,11 +1,10 @@
 """Text-to-speech: Speaches/Kokoro over HTTP (default) or embedded Piper.
 
 Output is always s16le mono PCM at settings.sample_rate (the device WS contract).
-Kokoro synthesizes at 24 kHz, so the speaches path resamples via audioop —
-which pins the runtime to Python 3.12 (audioop is removed in 3.13).
+The speaches path requests the target rate directly via the server's
+`sample_rate` extension, so no local resampling is needed.
 """
 
-import audioop
 import io
 import wave
 
@@ -35,6 +34,7 @@ def _synthesize_speaches(text: str) -> bytes:
             "voice": settings.tts_voice,
             "input": text,
             "response_format": "wav",
+            "sample_rate": settings.sample_rate,
         },
     )
     response.raise_for_status()
@@ -42,12 +42,12 @@ def _synthesize_speaches(text: str) -> bytes:
     with wave.open(io.BytesIO(response.content), "rb") as w:
         rate, channels, width = w.getframerate(), w.getnchannels(), w.getsampwidth()
         frames = w.readframes(w.getnframes())
-    if width != 2:
-        frames = audioop.lin2lin(frames, width, 2)
-    if channels == 2:
-        frames = audioop.tomono(frames, 2, 0.5, 0.5)
-    if rate != settings.sample_rate:
-        frames, _state = audioop.ratecv(frames, 2, 1, rate, settings.sample_rate, None)
+    if (rate, channels, width) != (settings.sample_rate, 1, 2):
+        raise RuntimeError(
+            f"Speaches returned {rate} Hz/{channels}ch/{8 * width}-bit audio; "
+            f"expected {settings.sample_rate} Hz mono 16-bit — check the server's "
+            "sample_rate support"
+        )
     return frames
 
 
@@ -61,4 +61,14 @@ def _synthesize_embedded(text: str) -> bytes:
     chunks = bytearray()
     for chunk in _embedded_voice.synthesize_stream_raw(text):
         chunks.extend(chunk)
-    return bytes(chunks)
+    native_rate = _embedded_voice.config.sample_rate
+    if native_rate == settings.sample_rate:
+        return bytes(chunks)
+
+    import numpy as np
+
+    audio = np.frombuffer(bytes(chunks), dtype=np.int16)
+    n_out = int(len(audio) * settings.sample_rate / native_rate)
+    positions = np.linspace(0, len(audio) - 1, n_out)
+    resampled = np.interp(positions, np.arange(len(audio)), audio.astype(np.float32))
+    return resampled.astype(np.int16).tobytes()