Windows TTS MCP Server

Instructions

Implementation Reference

• windows_tts_mcp/main.py:255-279 (handler)

  The primary handler for the 'speak_quiet' tool. Decorated with @mcp.tool() for automatic registration in FastMCP. Splits long text into chunks using split_text_for_tts, executes TTS playback in a background thread using a nested _speak_quiet helper that calls powershell_tts with volume=50 for quiet speech, and returns a status message.

  @mcp.tool()
  def speak_quiet(text: str) -> str:
      """텍스트를 작은 볼륨으로 읽어줍니다"""
      try:
          # 텍스트 분할
          text_chunks = split_text_for_tts(text, 400)
          total_chunks = len(text_chunks)
          
          def _speak_quiet():
              for i, chunk in enumerate(text_chunks, 1):
                  safe_print(f"[QUIET TTS] {i}/{total_chunks} 부분 재생 중: {chunk[:50]}...")
                  powershell_tts(chunk, rate=0, volume=50)  # 작은 볼륨
                  if i < total_chunks:
                      time.sleep(0.5)
          
          thread = threading.Thread(target=_speak_quiet, daemon=True)
          thread.start()
          
          if total_chunks > 1:
              return f"[QUIET] 작은 볼륨 재생 시작 ({total_chunks}개 부분): '{text[:50]}...'"
          else:
              return f"[QUIET] 작은 볼륨 재생 시작: '{text[:50]}...'"
          
      except Exception as e:
          return f"[ERROR] 작은 볼륨 재생 오류: {str(e)}"

• windows_tts_mcp/main.py:67-129 (helper)

  Core helper function that executes TTS via PowerShell with configurable rate and volume. Called by speak_quiet with rate=0, volume=50 to produce quiet speech. Handles process management, text escaping, and error handling.

  def powershell_tts(text: str, rate: int = 0, volume: int = 100) -> bool:
      """PowerShell을 사용한 TTS 실행"""
      process = None
      try:
          if platform.system() != "Windows":
              safe_print("[ERROR] Windows가 아닙니다")
              return False
          
          # 텍스트에서 작은따옴표 이스케이프 처리
          escaped_text = text.replace("'", "''")
          
          # PowerShell TTS 명령어
          cmd = [
              "powershell", "-Command",
              f"Add-Type -AssemblyName System.Speech; "
              f"$synth = New-Object System.Speech.Synthesis.SpeechSynthesizer; "
              f"$synth.Rate = {rate}; "
              f"$synth.Volume = {volume}; "
              f"$synth.Speak('{escaped_text}'); "
              f"$synth.Dispose()"
          ]
          
          # 프로세스 시작
          process = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
          
          # 실행 중인 프로세스 목록에 추가
          with process_lock:
              running_processes.append(process)
          
          # 프로세스 완료 대기
          stdout, stderr = process.communicate(timeout=180)
          
          # 완료된 프로세스 목록에서 제거
          with process_lock:
              if process in running_processes:
                  running_processes.remove(process)
          
          if process.returncode == 0:
              safe_print(f"[SUCCESS] TTS 완료: {text[:30]}...")
              return True
          else:
              safe_print(f"[ERROR] TTS 오류: {stderr}")
              return False
              
      except subprocess.TimeoutExpired:
          safe_print("[WARNING] TTS 시간 초과")
          if process:
              process.kill()
              with process_lock:
                  if process in running_processes:
                      running_processes.remove(process)
          return False
      except Exception as e:
          safe_print(f"[ERROR] TTS 예외: {e}")
          if process:
              try:
                  process.kill()
                  with process_lock:
                      if process in running_processes:
                          running_processes.remove(process)
              except:
                  pass
          return False

• windows_tts_mcp/main.py:131-168 (helper)

  Helper function to split long text into TTS-friendly chunks (max 500 chars by default, 400 for speak_quiet). Ensures natural sentence boundaries for smooth playback. Used by speak_quiet.

  def split_text_for_tts(text: str, max_length: int = 500) -> list:
      """텍스트를 TTS용으로 적절히 분할"""
      if len(text) <= max_length:
          return [text]
      
      # 문장 단위로 분할 시도
      import re
      sentences = re.split(r'[.!?。！？]\s*', text)
      
      chunks = []
      current_chunk = ""
      
      for sentence in sentences:
          # 문장이 너무 긴 경우 더 작게 분할
          if len(sentence) > max_length:
              # 쉼표나 기타 구두점으로 분할
              sub_parts = re.split(r'[,;:\s]\s*', sentence)
              for part in sub_parts:
                  if len(current_chunk + part) <= max_length:
                      current_chunk += part + " "
                  else:
                      if current_chunk.strip():
                          chunks.append(current_chunk.strip())
                      current_chunk = part + " "
          else:
              # 현재 청크에 문장을 추가할 수 있는지 확인
              if len(current_chunk + sentence) <= max_length:
                  current_chunk += sentence + ". "
              else:
                  if current_chunk.strip():
                      chunks.append(current_chunk.strip())
                  current_chunk = sentence + ". "
      
      # 마지막 청크 추가
      if current_chunk.strip():
          chunks.append(current_chunk.strip())
      
      return chunks