Replace ElevenLabs with local STT and TTS

python/local_tts_worker.py

@@ -0,0 +1,125 @@
+import base64
+import json
+import os
+import sys
+import tempfile
+import traceback
+
+
+os.environ.setdefault("PYTHONIOENCODING", "utf-8")
+
+
+def log(message: str) -> None:
+    print(message, file=sys.stderr, flush=True)
+
+
+def write_response(request_id: int, ok: bool, result=None, error: str | None = None) -> None:
+    payload = {
+        "id": request_id,
+        "ok": ok,
+    }
+    if ok:
+        payload["result"] = result
+    else:
+        payload["error"] = error or "unknown error"
+
+    sys.stdout.write(json.dumps(payload, ensure_ascii=False) + "\n")
+    sys.stdout.flush()
+
+
+class TtsWorker:
+    def __init__(self) -> None:
+        from melo.api import TTS
+
+        self.language = os.environ.get("LOCAL_TTS_LANGUAGE", "KR").strip() or "KR"
+        self.speaker_key = os.environ.get("LOCAL_TTS_SPEAKER", "KR").strip() or "KR"
+        self.device = os.environ.get("LOCAL_TTS_DEVICE", "auto").strip() or "auto"
+        self.speed = float(os.environ.get("LOCAL_TTS_SPEED", "1.12"))
+
+        self.model = TTS(language=self.language, device=self.device)
+        speaker_ids = self.model.hps.data.spk2id
+        self.speaker_id = speaker_ids.get(self.speaker_key)
+
+        if self.speaker_id is None:
+            normalized = self.speaker_key.upper()
+            self.speaker_id = speaker_ids.get(normalized)
+
+        if self.speaker_id is None:
+            self.speaker_id = next(iter(speaker_ids.values()))
+
+        log(
+            f"local-tts ready language={self.language} speaker={self.speaker_key} device={self.device} speed={self.speed}"
+        )
+
+    def synthesize(self, text: str) -> bytes:
+        temp_path = ""
+
+        try:
+            with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as handle:
+                temp_path = handle.name
+
+            self.model.tts_to_file(
+                text,
+                self.speaker_id,
+                temp_path,
+                speed=self.speed,
+                quiet=True,
+            )
+
+            with open(temp_path, "rb") as handle:
+                return handle.read()
+        finally:
+            if temp_path:
+                try:
+                    os.unlink(temp_path)
+                except OSError:
+                    pass
+
+
+def main() -> int:
+    try:
+        worker = TtsWorker()
+    except Exception as exc:
+        log("failed to initialize local TTS worker")
+        log("run `bun run setup:local-ai` first if dependencies are missing")
+        log("".join(traceback.format_exception(exc)))
+        return 1
+
+    for line in sys.stdin:
+        line = line.strip()
+        if not line:
+            continue
+
+        try:
+            request = json.loads(line)
+            request_id = int(request["id"])
+            method = request["method"]
+            params = request.get("params", {})
+
+            if method == "ping":
+                write_response(request_id, True, {"ready": True})
+                continue
+            if method != "synthesize":
+                raise ValueError(f"unsupported method: {method}")
+
+            text = str(params.get("text", "")).strip()
+            if not text:
+                raise ValueError("text is empty")
+
+            audio = worker.synthesize(text)
+            write_response(
+                request_id,
+                True,
+                {
+                    "wav_base64": base64.b64encode(audio).decode("ascii"),
+                },
+            )
+        except Exception as exc:
+            error_text = "".join(traceback.format_exception_only(type(exc), exc)).strip()
+            write_response(request_id, False, error=error_text)
+
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())