Update desktop app to android app capabilities.

bolt_pet/audio/stt.py

@@ -1,14 +1,20 @@
 """Speech-to-text for the actual query, after the wake word fires.
 
-Deepgram, same as desk_client/bolt_desk.py.
+The "guaranteed" fallback for when stt_stream's opportunistic live-feed
+session didn't produce a transcript (streaming disabled, or the socket
+never came up). There is no separate one-shot REST endpoint server-side any
+more — /desk/stt is a websocket relay only — so this connects the exact
+same way stt_stream.py does and just feeds the whole buffered utterance in
+one go instead of frame-by-frame as it's captured. That connection is
+unconditional (not gated by STT_STREAMING, which only controls the
+opportunistic optimisation), since there is nothing left to fall back to
+if it fails.
 """
 
 from __future__ import annotations
 
-import requests
-
 from .. import config
-from .mic import pcm_to_wav_bytes
+from . import stt_stream
 
 
 class SttError(Exception):
@@ -16,27 +22,12 @@ class SttError(Exception):
 
 
 def transcribe(pcm) -> str:
-    if not config.DEEPGRAM_API_KEY:
-        raise SttError("DEEPGRAM_API_KEY is not set")
+    if not config.is_configured():
+        raise SttError("BOLT_SERVER_URL / DESK_API_KEY not set")
     try:
-        response = requests.post(
-            "https://api.deepgram.com/v1/listen",
-            params={"model": config.DEEPGRAM_MODEL, "language": "en", "smart_format": "true"},
-            headers={
-                "Authorization": f"Token {config.DEEPGRAM_API_KEY}",
-                "Content-Type": "audio/wav",
-            },
-            data=pcm_to_wav_bytes(pcm),
-            timeout=30,
-        )
-        response.raise_for_status()
+        socket = stt_stream.connect()
     except Exception as exc:
-        raise SttError(f"transcription request failed: {exc}") from exc
-    try:
-        return (
-            response.json()
-            .get("results", {}).get("channels", [{}])[0]
-            .get("alternatives", [{}])[0].get("transcript", "")
-        ).strip()
-    except Exception as exc:
-        raise SttError(f"couldn't parse transcription response: {exc}") from exc
+        raise SttError(f"couldn't reach the transcription server: {exc}") from exc
+    session = stt_stream.StreamingTranscriber(socket)
+    session.feed(pcm)
+    return session.finish()