Update desktop app to android app capabilities.

bolt_pet/config.py

@@ -54,31 +54,41 @@ WAKE_WORD_THRESHOLD = float(os.environ.get("WAKE_WORD_THRESHOLD", "0.5"))
 # heartbeat poll in controller.py during quiet stretches with no wake word.
 WAKE_CHECK_INTERVAL_SECONDS = float(os.environ.get("WAKE_CHECK_INTERVAL_SECONDS", "1.2"))
 
-# ── STT (Deepgram, same as bolt_desk.py) ────────────────────────────────────
+# ── STT (server-hosted, same /desk/stt relay the Android app uses) ─────────
+# No local Deepgram account needed any more: audio/stt_stream.py opens a
+# websocket to this pet's own BOLT_SERVER_URL/DESK_API_KEY, which the server
+# relays to Deepgram and meters it against the same credit ledger as a chat turn.
+# There is no separate one-shot REST path server-side, so audio/stt.py's
+# "guaranteed" fallback uses this exact same connection too — just fed the
+# whole utterance at once instead of frame-by-frame.
 
-DEEPGRAM_API_KEY = os.environ.get("DEEPGRAM_API_KEY", "")
-DEEPGRAM_MODEL = os.environ.get("DEEPGRAM_MODEL", "nova-3")
-# Transcribe *while* you talk instead of uploading the finished clip: frames go
-# up as they are captured, so the transcript is ready the moment the VAD says
-# you stopped. Needs `websocket-client`; falls back to the one-shot upload
-# whenever it can't connect, so turning it on can only help.
+# Transcribe *while* you talk instead of waiting for the utterance to end:
+# frames go up as they are captured, so the transcript is ready the moment the
+# VAD says you stopped. Needs `websocket-client` (in requirements.txt); when
+# it can't connect the one-shot path (audio/stt.py) still tries the same
+# server relay itself, so turning this off only costs latency, not the
+# ability to transcribe at all.
 STT_STREAMING = os.environ.get("STT_STREAMING", "true").lower() in ("1", "true", "yes", "on")
 
-# ── TTS (ElevenLabs, requested as raw PCM so playback needs no external
-# player binary — cross-platform via sounddevice instead of shelling out to
-# mpv/ffplay like bolt_desk.py does on Linux) ───────────────────────────────
+# ── TTS (server-hosted, same /desk/tts endpoint the Android app uses) ──────
+# No local ElevenLabs account needed for the normal reply voice any more —
+# audio/tts.py posts to this pet's own BOLT_SERVER_URL/DESK_API_KEY and gets
+# back raw 16 kHz mono PCM16, same as the phone. Falls back to offline
+# pyttsx3 if the server call fails.
+#
+# ELEVENLABS_API_KEY is still read directly by this client for exactly one
+# feature the server has no endpoint for: multi-voice `dialoguectl` scenes
+# (audio/tts.synthesize_dialogue, see dialogue.py) — leave it blank and
+# everything except that one feature works with zero local API keys.
 
 ELEVENLABS_API_KEY = os.environ.get("ELEVENLABS_API_KEY", "")
+# Which voice to ask the server for — an ElevenLabs voice id (or a "vb:"-
+# prefixed cloned voice, if this desk key owns one). The server picks the
+# synthesis model itself now; there is nothing left for this client to choose.
 ELEVENLABS_VOICE_ID = os.environ.get("ELEVENLABS_VOICE_ID", "")
-ELEVENLABS_MODEL_ID = os.environ.get("ELEVENLABS_MODEL_ID", "eleven_flash_v2")
-# eleven_flash_v2 is English-only, and the two cases that swap the voice
-# (server-picked `speak_as`, or a reply with non-ASCII in it) are usually
-# exactly the cases where the reply isn't English — see tts.model_for().
-ELEVENLABS_MULTILINGUAL_MODEL_ID = os.environ.get(
-    "ELEVENLABS_MULTILINGUAL_MODEL_ID", "eleven_flash_v2_5"
-)
-# ElevenLabs PCM output formats are named pcm_<sample_rate>.
-TTS_SAMPLE_RATE = int(os.environ.get("TTS_SAMPLE_RATE", "24000"))
+# Fixed by the server (ai/desk_media.py's PCM_SAMPLE_RATE) — not a free
+# tunable any more, but still an env override in case that ever changes.
+TTS_SAMPLE_RATE = int(os.environ.get("TTS_SAMPLE_RATE", "16000"))
 
 # Does a voice the server picks (its speak_as marker — "talk like a pirate",
 # "say that in Japanese") stay on for later replies, or last one reply only?