myagent-ai 1.15.65 → 1.15.66

package/core/deps_checker.py

@@ -76,7 +76,9 @@ DEPENDENCIES: List[DepInfo] = [
 
     # ── 语音识别 (STT) ──
     DepInfo("faster_whisper", "faster-whisper", "1.0.0", "stt", "all",
-            note="本地语音识别引擎 (首次使用自动下载模型)"),
+            note="本地语音识别引擎 (需要 C++ 编译)"),
+    DepInfo("speech_recognition", "SpeechRecognition", "3.10.0", "stt", "all",
+            note="在线语音识别 (Google API，纯 Python 无需编译，Termux 兼容)"),
 
     # ── 浏览器自动化 (ChromeDev MCP) ──
     # Playwright 已移除，浏览器自动化统一使用 ChromeDevTools Protocol (MCP)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "myagent-ai",
-  "version": "1.15.65",
+  "version": "1.15.66",
   "description": "本地桌面端执行型AI助手 - Open Interpreter 风格 | Local Desktop Execution-Oriented AI Assistant",
   "main": "main.py",
   "bin": {

package/web/api_server.py

@@ -1219,11 +1219,41 @@ class ApiServer:
             except Exception as e:
                 logger.warning(f"vosk 转录失败: {e}")
 
+            # ── 尝试 SpeechRecognition (Google Web Speech API, 纯 Python 无需编译) ──
+            try:
+                import speech_recognition as sr
+                wav_buf = io.BytesIO(audio_data)
+                try:
+                    audio_buf = io.BytesIO(audio_data)
+                    from pydub import AudioSegment
+                    seg = AudioSegment.from_file(audio_buf, format=audio_format or "webm")
+                    seg = seg.set_channels(1).set_frame_rate(16000).set_sample_width(2)
+                    seg.export(wav_buf, format="wav")
+                except Exception:
+                    wav_buf = io.BytesIO(audio_data)
+                wav_buf.seek(0)
+                recognizer = sr.Recognizer()
+                with sr.AudioFile(wav_buf) as source:
+                    audio = recognizer.record(source)
+                text = recognizer.recognize_google(audio, language="zh-CN")
+                if text:
+                    logger.info("SpeechRecognition (Google API) 转录成功")
+                    return web.json_response({"text": text, "engine": "speech_recognition"})
+            except ImportError:
+                logger.debug("SpeechRecognition 未安装，跳过")
+            except sr.UnknownValueError:
+                logger.debug("SpeechRecognition 无法识别音频内容")
+            except sr.RequestError as e:
+                logger.warning(f"SpeechRecognition API 请求失败: {e}")
+            except Exception as e:
+                logger.warning(f"SpeechRecognition 转录失败: {e}")
+
             # ── 没有可用的 STT 引擎 ──
             return web.json_response({
-                "error": "未检测到本地 STT 引擎。请安装 faster-whisper（推荐）或 vosk：\n"
-                         "  pip install faster-whisper  (首次使用会自动下载 tiny 模型 ~39MB)\n"
-                         "  或 pip install vosk",
+                "error": "未检测到本地 STT 引擎。请安装以下任一引擎：\n"
+                         "  pip install faster-whisper  (推荐，离线，首次下载模型 ~39MB)\n"
+                         "  pip install vosk             (离线，需下载模型)\n"
+                         "  pip install SpeechRecognition (在线，使用 Google API，无需编译)",
                 "available": False,
             }, status=503)