Add text-to-dialogue, self-restart capability, and misc updates

tests/test_tts_stream.py

@@ -8,7 +8,8 @@ import numpy as np
 
 sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
 
-from bolt_pet.audio.tts import chunks_to_int16
+from bolt_pet import config as tts_config
+from bolt_pet.audio.tts import chunks_to_int16, model_for, voice_for
 from bolt_pet.audio.wake_word import NearMissLog
 
 
@@ -80,3 +81,27 @@ def test_clear_resets_peak_and_entries():
     log.observe(0.45, threshold=0.5, timestamp=1.0)
     log.clear()
     assert log.entries() == [] and log.peak == 0.0
+
+
+# ── voice / model selection (server speak_as) ───────────────────────────────
+
+def test_the_override_voice_wins_over_the_configured_one(monkeypatch):
+    monkeypatch.setattr(tts_config, "ELEVENLABS_VOICE_ID", "DEFAULT")
+    assert voice_for("VOICE1") == "VOICE1"
+    assert voice_for("") == "DEFAULT"
+    assert voice_for(None) == "DEFAULT"
+
+
+def test_english_replies_in_the_default_voice_use_the_default_model(monkeypatch):
+    monkeypatch.setattr(tts_config, "ELEVENLABS_MODEL_ID", "eleven_flash_v2")
+    monkeypatch.setattr(tts_config, "ELEVENLABS_MULTILINGUAL_MODEL_ID", "eleven_flash_v2_5")
+    assert model_for("all good here", None) == "eleven_flash_v2"
+
+
+def test_a_picked_voice_or_non_english_text_uses_the_multilingual_model(monkeypatch):
+    # eleven_flash_v2 is English-only: it would read either of these as
+    # mangled phonetic English rather than failing outright.
+    monkeypatch.setattr(tts_config, "ELEVENLABS_MODEL_ID", "eleven_flash_v2")
+    monkeypatch.setattr(tts_config, "ELEVENLABS_MULTILINGUAL_MODEL_ID", "eleven_flash_v2_5")
+    assert model_for("all good here", "VOICE1") == "eleven_flash_v2_5"
+    assert model_for("こんにちは", None) == "eleven_flash_v2_5"