first

speech_to_speech/api/openai_realtime/delay_fillers.py

@@ -0,0 +1,84 @@
+from __future__ import annotations
+
+import logging
+import os
+from dataclasses import dataclass
+from typing import Any
+
+import numpy as np
+
+from speech_to_speech.pipeline.messages import TTSInput
+
+logger = logging.getLogger(__name__)
+
+_TRUE_VALUES = {"1", "true", "yes", "on"}
+
+
+@dataclass(slots=True)
+class DelayFillerConfig:
+    enabled: bool
+    threshold_s: float
+    short_phrases: list[str]
+    full_phrases: list[str]
+
+
+def _split_env_list(name: str) -> list[str]:
+    raw = os.environ.get(name, "").strip()
+    return [part.strip() for part in raw.split("|") if part.strip()]
+
+
+def _env_flag(name: str, *, default: bool) -> bool:
+    raw = os.environ.get(name)
+    if raw is None:
+        return default
+    return raw.strip().lower() in _TRUE_VALUES
+
+
+def load_delay_filler_config() -> DelayFillerConfig:
+    short_phrases = _split_env_list("TTS_DELAY_FILLERS_SHORT_ES")
+    full_phrases = _split_env_list("TTS_DELAY_FILLERS_FULL_ES")
+
+    # Backward compatibility with the old single-list variable.
+    if not short_phrases and not full_phrases:
+        full_phrases = _split_env_list("TTS_DELAY_FILLERS_ES")
+
+    enabled = _env_flag("TTS_DELAY_FILLERS_ENABLED", default=bool(short_phrases or full_phrases))
+    threshold_ms_raw = os.environ.get("TTS_DELAY_FILLERS_THRESHOLD_MS", "1200").strip() or "1200"
+    try:
+        threshold_ms = max(0, int(threshold_ms_raw))
+    except ValueError:
+        logger.warning("Invalid TTS_DELAY_FILLERS_THRESHOLD_MS=%r; using 1200", threshold_ms_raw)
+        threshold_ms = 1200
+    return DelayFillerConfig(
+        enabled=enabled and bool(short_phrases or full_phrases),
+        threshold_s=threshold_ms / 1000.0,
+        short_phrases=short_phrases,
+        full_phrases=full_phrases,
+    )
+
+
+def _chunk_to_bytes(chunk: Any) -> bytes:
+    audio = getattr(chunk, "audio", chunk)
+    if isinstance(audio, np.ndarray) or hasattr(audio, "tobytes"):
+        return audio.tobytes()
+    if isinstance(audio, bytes):
+        return audio
+    raise TypeError(f"Unsupported delay filler audio chunk type: {type(audio)!r}")
+
+
+def pregenerate_delay_filler_clips(tts_handler: Any, phrases: list[str]) -> list[bytes]:
+    clips: list[bytes] = []
+    for phrase in phrases:
+        try:
+            clip = b"".join(
+                _chunk_to_bytes(chunk)
+                for chunk in tts_handler.process(TTSInput(text=phrase, language_code="es"))
+            )
+        except Exception:
+            logger.exception("Failed to pregenerate TTS delay filler for phrase %r", phrase)
+            continue
+        if not clip:
+            logger.warning("Discarding empty TTS delay filler for phrase %r", phrase)
+            continue
+        clips.append(clip)
+    return clips