feat(engine): 添加GLM-ASR语音识别引擎支持

- 新增GLM-ASR云端语音识别引擎实现 - 扩展配置界面添加GLM相关参数设置 - Ollama支持自定义域名和Apikey以支持云端和其他LLM - 修改音频处理逻辑以支持新引擎 - 更新依赖项和构建配置 - 修复Ollama翻译功能相关问题
2026-02-04 03:56:11 +08:00 · 2026-01-10 16:02:24 +08:00
parent 383e582a2d
commit 0825e48902
19 changed files with 519 additions and 91 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -8,7 +8,14 @@ __pycache__
 .venv
 test.py
 engine/build
+engine/dist
+engine/.venv
+engine/__pycache__
+engine/portaudio
+package-lock.json
+engine/pyinstaller_cache
 engine/models
 engine/notebook
 .repomap
 .virtualme
+engine/main.spec
--- a/build/entitlements.mac.plist
+++ b/build/entitlements.mac.plist
@@ -8,5 +8,9 @@
    <true/>
    <key>com.apple.security.cs.allow-dyld-environment-variables</key>
    <true/>
+    <key>com.apple.security.cs.disable-library-validation</key>
+    <true/>
+    <key>com.apple.security.device.audio-input</key>
+    <true/>
  </dict>
-</plist>
+</plist>
--- a/engine/audio2text/init.py
+++ b/engine/audio2text/init.py
@@ -1,3 +1,4 @@
 from .gummy import GummyRecognizer
 from .vosk import VoskRecognizer
-from .sosv import SosvRecognizer
+from .sosv import SosvRecognizer
+from .glm import GlmRecognizer
--- a/engine/audio2text/glm.py
+++ b/engine/audio2text/glm.py
@@ -0,0 +1,163 @@
+import threading
+import io
+import wave
+import struct
+import math
+import audioop
+import requests
+from datetime import datetime
+
+from utils import shared_data
+from utils import stdout_cmd, stdout_obj, google_translate, ollama_translate
+
+class GlmRecognizer:
+    """
+    使用 GLM-ASR 引擎处理音频数据，并在标准输出中输出 Auto Caption 软件可读取的 JSON 字符串数据
+
+    初始化参数：
+        url: GLM-ASR API URL
+        model: GLM-ASR 模型名称
+        api_key: GLM-ASR API Key
+        source: 源语言
+        target: 目标语言
+        trans_model: 翻译模型名称
+        ollama_name: Ollama 模型名称
+    """
+    def __init__(self, url: str, model: str, api_key: str, source: str, target: str | None, trans_model: str, ollama_name: str, ollama_url: str = '', ollama_api_key: str = ''):
+        self.url = url
+        self.model = model
+        self.api_key = api_key
+        self.source = source
+        self.target = target
+        if trans_model == 'google':
+            self.trans_func = google_translate
+        else:
+            self.trans_func = ollama_translate
+        self.ollama_name = ollama_name
+        self.ollama_url = ollama_url
+        self.ollama_api_key = ollama_api_key
+        
+        self.audio_buffer = []
+        self.is_speech = False
+        self.silence_frames = 0
+        self.speech_start_time = None
+        self.time_str = ''
+        self.cur_id = 0
+        
+        # VAD settings (假设 16k 16bit, chunk size 1024 or similar)
+        # 16bit = 2 bytes per sample.
+        # RMS threshold needs tuning. 500 is a conservative guess for silence.
+        self.threshold = 500 
+        self.silence_limit = 15 # frames (approx 0.5-1s depending on chunk size)
+        self.min_speech_frames = 10 # frames
+
+    def start(self):
+        """启动 GLM 引擎"""
+        stdout_cmd('info', 'GLM-ASR recognizer started.')
+
+    def stop(self):
+        """停止 GLM 引擎"""
+        stdout_cmd('info', 'GLM-ASR recognizer stopped.')
+
+    def process_audio(self, chunk):
+        # chunk is bytes (int16)
+        rms = audioop.rms(chunk, 2)
+        
+        if rms > self.threshold:
+            if not self.is_speech:
+                self.is_speech = True
+                self.time_str = datetime.now().strftime('%H:%M:%S.%f')[:-3]
+                self.audio_buffer = []
+            self.audio_buffer.append(chunk)
+            self.silence_frames = 0
+        else:
+            if self.is_speech:
+                self.audio_buffer.append(chunk)
+                self.silence_frames += 1
+                if self.silence_frames > self.silence_limit:
+                    # Speech ended
+                    if len(self.audio_buffer) > self.min_speech_frames:
+                        self.recognize(self.audio_buffer, self.time_str)
+                    self.is_speech = False
+                    self.audio_buffer = []
+                    self.silence_frames = 0
+    
+    def recognize(self, audio_frames, time_s):
+        audio_bytes = b''.join(audio_frames)
+        
+        wav_io = io.BytesIO()
+        with wave.open(wav_io, 'wb') as wav_file:
+            wav_file.setnchannels(1)
+            wav_file.setsampwidth(2)
+            wav_file.setframerate(16000)
+            wav_file.writeframes(audio_bytes)
+        wav_io.seek(0)
+        
+        threading.Thread(
+            target=self._do_request, 
+            args=(wav_io.read(), time_s, self.cur_id)
+        ).start()
+        self.cur_id += 1
+
+    def _do_request(self, audio_content, time_s, index):
+        try:
+            files = {
+                'file': ('audio.wav', audio_content, 'audio/wav')
+            }
+            data = {
+                'model': self.model,
+                'stream': 'false'
+            }
+            headers = {
+                'Authorization': f'Bearer {self.api_key}'
+            }
+            
+            response = requests.post(self.url, headers=headers, data=data, files=files, timeout=15)
+            
+            if response.status_code == 200:
+                res_json = response.json()
+                text = res_json.get('text', '')
+                if text:
+                    self.output_caption(text, time_s, index)
+            else:
+                try:
+                    err_msg = response.json()
+                    stdout_cmd('error', f"GLM API Error: {err_msg}")
+                except:
+                    stdout_cmd('error', f"GLM API Error: {response.text}")
+                
+        except Exception as e:
+            stdout_cmd('error', f"GLM Request Failed: {str(e)}")
+
+    def output_caption(self, text, time_s, index):
+        caption = {
+            'command': 'caption',
+            'index': index,
+            'time_s': time_s,
+            'time_t': datetime.now().strftime('%H:%M:%S.%f')[:-3],
+            'text': text,
+            'translation': ''
+        }
+        
+        if self.target:
+             if self.trans_func == ollama_translate:
+                 th = threading.Thread(
+                    target=self.trans_func,
+                    args=(self.ollama_name, self.target, caption['text'], time_s, self.ollama_url, self.ollama_api_key),
+                    daemon=True
+                )
+             else:
+                 th = threading.Thread(
+                    target=self.trans_func,
+                    args=(self.ollama_name, self.target, caption['text'], time_s),
+                    daemon=True
+                )
+             th.start()
+        
+        stdout_obj(caption)
+
+    def translate(self):
+        global shared_data
+        while shared_data.status == 'running':
+            chunk = shared_data.chunk_queue.get()
+            self.process_audio(chunk)
--- a/engine/audio2text/sosv.py
+++ b/engine/audio2text/sosv.py
@@ -29,7 +29,7 @@ class SosvRecognizer:
        trans_model: 翻译模型名称
        ollama_name: Ollama 模型名称
    """
-    def __init__(self, model_path: str, source: str, target: str | None, trans_model: str, ollama_name: str):
+    def __init__(self, model_path: str, source: str, target: str | None, trans_model: str, ollama_name: str, ollama_url: str = '', ollama_api_key: str = ''):
        if model_path.startswith('"'):
            model_path = model_path[1:]
        if model_path.endswith('"'):
@@ -45,6 +45,8 @@ class SosvRecognizer:
        else:
            self.trans_func = ollama_translate
        self.ollama_name = ollama_name
+        self.ollama_url = ollama_url
+        self.ollama_api_key = ollama_api_key
        self.time_str = ''
        self.cur_id = 0
        self.prev_content = ''
@@ -152,7 +154,7 @@ class SosvRecognizer:
                if self.target:
                    th = threading.Thread(
                        target=self.trans_func,
-                        args=(self.ollama_name, self.target, caption['text'], self.time_str),
+                        args=(self.ollama_name, self.target, caption['text'], self.time_str, self.ollama_url, self.ollama_api_key),
                        daemon=True
                    )
                    th.start()    
--- a/engine/audio2text/vosk.py
+++ b/engine/audio2text/vosk.py
@@ -18,7 +18,7 @@ class VoskRecognizer:
        trans_model: 翻译模型名称
        ollama_name: Ollama 模型名称
    """
-    def __init__(self, model_path: str, target: str | None, trans_model: str, ollama_name: str):
+    def __init__(self, model_path: str, target: str | None, trans_model: str, ollama_name: str, ollama_url: str = '', ollama_api_key: str = ''):
        SetLogLevel(-1)
        if model_path.startswith('"'):
            model_path = model_path[1:]
@@ -31,6 +31,8 @@ class VoskRecognizer:
        else:
            self.trans_func = ollama_translate
        self.ollama_name = ollama_name
+        self.ollama_url = ollama_url
+        self.ollama_api_key = ollama_api_key
        self.time_str = ''
        self.cur_id = 0
        self.prev_content = ''
@@ -66,7 +68,7 @@ class VoskRecognizer:
            if self.target:
                th = threading.Thread(
                    target=self.trans_func,
-                    args=(self.ollama_name, self.target, caption['text'], self.time_str),
+                    args=(self.ollama_name, self.target, caption['text'], self.time_str, self.ollama_url, self.ollama_api_key),
                    daemon=True
                )
                th.start()
--- a/engine/main.py
+++ b/engine/main.py
@@ -8,6 +8,7 @@ from utils import merge_chunk_channels, resample_chunk_mono
 from audio2text import GummyRecognizer
 from audio2text import VoskRecognizer
 from audio2text import SosvRecognizer
+from audio2text import GlmRecognizer
 from sysaudio import AudioStream


@@ -74,7 +75,7 @@ def main_gummy(s: str, t: str, a: int, c: int, k: str, r: bool, rp: str):
    engine.stop()


-def main_vosk(a: int, c: int, vosk: str, t: str, tm: str, omn: str, r: bool, rp: str):
+def main_vosk(a: int, c: int, vosk: str, t: str, tm: str, omn: str, ourl: str, okey: str, r: bool, rp: str):
    """
    Parameters:
        a: Audio source: 0 for output, 1 for input
@@ -83,14 +84,16 @@ def main_vosk(a: int, c: int, vosk: str, t: str, tm: str, omn: str, r: bool, rp:
        t: Target language
        tm: Translation model type, ollama or google
        omn: Ollama model name
+        ourl: Ollama Base URL
+        okey: Ollama API Key
        r: Whether to record the audio
        rp: Path to save the recorded audio
    """
    stream = AudioStream(a, c)
    if t == 'none':
-        engine = VoskRecognizer(vosk, None, tm, omn)
+        engine = VoskRecognizer(vosk, None, tm, omn, ourl, okey)
    else:
-        engine = VoskRecognizer(vosk, t, tm, omn)
+        engine = VoskRecognizer(vosk, t, tm, omn, ourl, okey)

    engine.start()
    stream_thread = threading.Thread(
@@ -106,7 +109,7 @@ def main_vosk(a: int, c: int, vosk: str, t: str, tm: str, omn: str, r: bool, rp:
    engine.stop()


-def main_sosv(a: int, c: int, sosv: str, s: str, t: str, tm: str, omn: str, r: bool, rp: str):
+def main_sosv(a: int, c: int, sosv: str, s: str, t: str, tm: str, omn: str, ourl: str, okey: str, r: bool, rp: str):
    """
    Parameters:
        a: Audio source: 0 for output, 1 for input
@@ -116,14 +119,16 @@ def main_sosv(a: int, c: int, sosv: str, s: str, t: str, tm: str, omn: str, r: b
        t: Target language
        tm: Translation model type, ollama or google
        omn: Ollama model name
+        ourl: Ollama API URL
+        okey: Ollama API Key
        r: Whether to record the audio
        rp: Path to save the recorded audio
    """
    stream = AudioStream(a, c)
    if t == 'none':
-        engine = SosvRecognizer(sosv, s, None, tm, omn)
+        engine = SosvRecognizer(sosv, s, None, tm, omn, ourl, okey)
    else:
-        engine = SosvRecognizer(sosv, s, t, tm, omn)
+        engine = SosvRecognizer(sosv, s, t, tm, omn, ourl, okey)

    engine.start()
    stream_thread = threading.Thread(
@@ -139,16 +144,54 @@ def main_sosv(a: int, c: int, sosv: str, s: str, t: str, tm: str, omn: str, r: b
    engine.stop()


+def main_glm(a: int, c: int, url: str, model: str, key: str, s: str, t: str, tm: str, omn: str, ourl: str, okey: str, r: bool, rp: str):
+    """
+    Parameters:
+        a: Audio source
+        c: Chunk rate
+        url: GLM API URL
+        model: GLM Model Name
+        key: GLM API Key
+        s: Source language
+        t: Target language
+        tm: Translation model
+        omn: Ollama model name
+        ourl: Ollama API URL
+        okey: Ollama API Key
+        r: Record
+        rp: Record path
+    """
+    stream = AudioStream(a, c)
+    if t == 'none':
+        engine = GlmRecognizer(url, model, key, s, None, tm, omn, ourl, okey)
+    else:
+        engine = GlmRecognizer(url, model, key, s, t, tm, omn, ourl, okey)
+    
+    engine.start()
+    stream_thread = threading.Thread(
+        target=audio_recording,
+        args=(stream, True, r, rp),
+        daemon=True
+    )
+    stream_thread.start()
+    try:
+        engine.translate()
+    except KeyboardInterrupt:
+        stdout("Keyboard interrupt detected. Exiting...")
+    engine.stop()
+
+
+
 if __name__ == "__main__":
    parser = argparse.ArgumentParser(description='Convert system audio stream to text')
    # all
    parser.add_argument('-e', '--caption_engine', default='gummy', help='Caption engine: gummy or vosk or sosv')
-    parser.add_argument('-a', '--audio_type', default=0, help='Audio stream source: 0 for output, 1 for input')
-    parser.add_argument('-c', '--chunk_rate', default=10, help='Number of audio stream chunks collected per second')
-    parser.add_argument('-p', '--port', default=0, help='The port to run the server on, 0 for no server')
-    parser.add_argument('-d', '--display_caption', default=0, help='Display caption on terminal, 0 for no display, 1 for display')
+    parser.add_argument('-a', '--audio_type', type=int, default=0, help='Audio stream source: 0 for output, 1 for input')
+    parser.add_argument('-c', '--chunk_rate', type=int, default=10, help='Number of audio stream chunks collected per second')
+    parser.add_argument('-p', '--port', type=int, default=0, help='The port to run the server on, 0 for no server')
+    parser.add_argument('-d', '--display_caption', type=int, default=0, help='Display caption on terminal, 0 for no display, 1 for display')
    parser.add_argument('-t', '--target_language', default='none', help='Target language code, "none" for no translation')
-    parser.add_argument('-r', '--record', default=0, help='Whether to record the audio, 0 for no recording, 1 for recording')
+    parser.add_argument('-r', '--record', type=int, default=0, help='Whether to record the audio, 0 for no recording, 1 for recording')
    parser.add_argument('-rp', '--record_path', default='', help='Path to save the recorded audio')
    # gummy and sosv
    parser.add_argument('-s', '--source_language', default='auto', help='Source language code')
@@ -157,20 +200,24 @@ if __name__ == "__main__":
    # vosk and sosv
    parser.add_argument('-tm', '--translation_model', default='ollama', help='Model for translation: ollama or google')
    parser.add_argument('-omn', '--ollama_name', default='', help='Ollama model name for translation')
+    parser.add_argument('-ourl', '--ollama_url', default='', help='Ollama API URL')
+    parser.add_argument('-okey', '--ollama_api_key', default='', help='Ollama API Key')
    # vosk only
    parser.add_argument('-vosk', '--vosk_model', default='', help='The path to the vosk model.')
    # sosv only
    parser.add_argument('-sosv', '--sosv_model', default=None, help='The SenseVoice model path')
+    # glm only
+    parser.add_argument('-gurl', '--glm_url', default='https://open.bigmodel.cn/api/paas/v4/audio/transcriptions', help='GLM API URL')
+    parser.add_argument('-gmodel', '--glm_model', default='glm-asr-2512', help='GLM Model Name')
+    parser.add_argument('-gkey', '--glm_api_key', default='', help='GLM API Key')

    args = parser.parse_args()
-    if int(args.port) == 0:
-        shared_data.status = "running"
-    else:
-        start_server(int(args.port))
-    
-    if int(args.display_caption) != 0:
+
+    if args.port != 0:
+        threading.Thread(target=start_server, args=(args.port,), daemon=True).start()
+
+    if args.display_caption == '1':
        change_caption_display(True)
-        print("Caption will be displayed on terminal")

    if args.caption_engine == 'gummy':
        main_gummy(
@@ -179,7 +226,7 @@ if __name__ == "__main__":
            int(args.audio_type),
            int(args.chunk_rate),
            args.api_key,
-            True if int(args.record) == 1 else False,
+            bool(int(args.record)),
            args.record_path
        )
    elif args.caption_engine == 'vosk':
@@ -190,7 +237,9 @@ if __name__ == "__main__":
            args.target_language,
            args.translation_model,
            args.ollama_name,
-            True if int(args.record) == 1 else False,
+            args.ollama_url,
+            args.ollama_api_key,
+            bool(int(args.record)),
            args.record_path
        )
    elif args.caption_engine == 'sosv':
@@ -202,7 +251,25 @@ if __name__ == "__main__":
            args.target_language,
            args.translation_model,
            args.ollama_name,
-            True if int(args.record) == 1 else False,
+            args.ollama_url,
+            args.ollama_api_key,
+            bool(int(args.record)),
+            args.record_path
+        )
+    elif args.caption_engine == 'glm':
+        main_glm(
+            int(args.audio_type),
+            int(args.chunk_rate),
+            args.glm_url,
+            args.glm_model,
+            args.glm_api_key,
+            args.source_language,
+            args.target_language,
+            args.translation_model,
+            args.ollama_name,
+            args.ollama_url,
+            args.ollama_api_key,
+            bool(int(args.record)),
            args.record_path
        )
    else:
--- a/engine/main.spec
+++ b/engine/main.spec
@@ -6,11 +6,17 @@ import sys
 if sys.platform == 'win32':
    vosk_path = str(Path('./.venv/Lib/site-packages/vosk').resolve())
 else:
-    vosk_path = str(Path('./.venv/lib/python3.12/site-packages/vosk').resolve())
+    venv_lib = Path('./.venv/lib')
+    python_dirs = list(venv_lib.glob('python*'))
+    if python_dirs:
+        vosk_path = str((python_dirs[0] / 'site-packages' / 'vosk').resolve())
+    else:
+        vosk_path = str(Path('./.venv/lib/python3.12/site-packages/vosk').resolve())

 a = Analysis(
    ['main.py'],
    pathex=[],
+    # binaries=[('portaudio/lib/.libs/libportaudio.2.dylib', '.')],
    binaries=[],
    datas=[(vosk_path, 'vosk')],
    hiddenimports=[],
@@ -27,21 +33,27 @@ pyz = PYZ(a.pure)
 exe = EXE(
    pyz,
    a.scripts,
-    a.binaries,
-    a.datas,
    [],
+    exclude_binaries=True,
    name='main',
    debug=False,
    bootloader_ignore_signals=False,
    strip=False,
    upx=True,
-    upx_exclude=[],
-    runtime_tmpdir=None,
    console=True,
    disable_windowed_traceback=False,
    argv_emulation=False,
    target_arch=None,
    codesign_identity=None,
    entitlements_file=None,
-    onefile=True,
+)
+
+coll = COLLECT(
+    exe,
+    a.binaries,
+    a.datas,
+    strip=False,
+    upx=True,
+    upx_exclude=[],
+    name='main',
 )
--- a/engine/requirements.txt
+++ b/engine/requirements.txt
@@ -7,4 +7,6 @@ pyaudio; sys_platform == 'darwin'
 pyaudiowpatch; sys_platform == 'win32'
 googletrans
 ollama
-sherpa_onnx
+sherpa_onnx
+requests
+openai
--- a/engine/utils/sysout.py
+++ b/engine/utils/sysout.py
@@ -47,7 +47,6 @@ def translation_display(obj):

 def stdout_obj(obj):
    global display_caption
-    print(obj['command'], display_caption)
    if obj['command'] == 'caption' and display_caption:
        caption_display(obj)
        return
--- a/engine/utils/translation.py
+++ b/engine/utils/translation.py
@@ -1,5 +1,9 @@
-from ollama import chat
+from ollama import chat, Client
 from ollama import ChatResponse
+try:
+    from openai import OpenAI
+except ImportError:
+    OpenAI = None
 import asyncio
 from googletrans import Translator
 from .sysout import stdout_cmd, stdout_obj
@@ -17,15 +21,43 @@ lang_map = {
    'zh-cn': 'Chinese'
 }

-def ollama_translate(model: str, target: str, text: str, time_s: str):
-    response: ChatResponse = chat(
-        model=model,
-        messages=[
-            {"role": "system", "content": f"/no_think Translate the following content into {lang_map[target]}, and do not output any additional information."},
-            {"role": "user", "content": text}
-        ]
-    )
-    content = response.message.content or ""
+def ollama_translate(model: str, target: str, text: str, time_s: str, url: str = '', key: str = ''):
+    content = ""
+    try:
+        if url:
+            if OpenAI:
+                client = OpenAI(base_url=url, api_key=key if key else "ollama")
+                response = client.chat.completions.create(
+                    model=model,
+                    messages=[
+                        {"role": "system", "content": f"/no_think Translate the following content into {lang_map[target]}, and do not output any additional information."},
+                        {"role": "user", "content": text}
+                    ]
+                )
+                content = response.choices[0].message.content or ""
+            else:
+                client = Client(host=url)
+                response: ChatResponse = client.chat(
+                    model=model,
+                    messages=[
+                        {"role": "system", "content": f"/no_think Translate the following content into {lang_map[target]}, and do not output any additional information."},
+                        {"role": "user", "content": text}
+                    ]
+                )
+                content = response.message.content or ""
+        else:
+            response: ChatResponse = chat(
+                model=model,
+                messages=[
+                    {"role": "system", "content": f"/no_think Translate the following content into {lang_map[target]}, and do not output any additional information."},
+                    {"role": "user", "content": text}
+                ]
+            )
+            content = response.message.content or ""
+    except Exception as e:
+        stdout_cmd("warn", f"Translation failed: {str(e)}")
+        return
+
    if content.startswith('<think>'):
        index = content.find('</think>')
        if index != -1:
--- a/package-lock.json
+++ b/package-lock.json
@@ -110,6 +110,7 @@
      "integrity": "sha512-IaaGWsQqfsQWVLqMn9OB92MNN7zukfVA4s7KKAI0KfrrDsZ0yhi5uV4baBuLuN7n3vsZpwP8asPPcVwApxvjBQ==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "@ampproject/remapping": "^2.2.0",
        "@babel/code-frame": "^7.27.1",
@@ -2274,6 +2275,7 @@
      "resolved": "https://registry.npmmirror.com/@types/node/-/node-22.15.17.tgz",
      "integrity": "sha512-wIX2aSZL5FE+MR0JlvF87BNVrtFWf6AE6rxSE9X7OwnVvoyCQjpzSRJ+M87se/4QCkCiebQAqrJ0y6fwIyi7nw==",
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "undici-types": "~6.21.0"
      }
@@ -2360,6 +2362,7 @@
      "integrity": "sha512-B2MdzyWxCE2+SqiZHAjPphft+/2x2FlO9YBx7eKE1BCb+rqBlQdhtAEhzIEdozHd55DXPmxBdpMygFJjfjjA9A==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "@typescript-eslint/scope-manager": "8.32.0",
        "@typescript-eslint/types": "8.32.0",
@@ -2791,6 +2794,7 @@
      "integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "bin": {
        "acorn": "bin/acorn"
      },
@@ -2851,6 +2855,7 @@
      "integrity": "sha512-j3fVLgvTo527anyYyJOGTYJbG+vnnQYvE0m5mmkc1TK+nxAppkCLMIL0aZ4dblVCNoGShhm+kzE4ZUykBoMg4g==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "fast-deep-equal": "^3.1.1",
        "fast-json-stable-stringify": "^2.0.0",
@@ -3064,7 +3069,6 @@
      "integrity": "sha512-+25nxyyznAXF7Nef3y0EbBeqmGZgeN/BxHX29Rs39djAfaFalmQ89SE6CWyDCHzGL0yt/ycBtNOmGTW0FyGWNw==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "archiver-utils": "^2.1.0",
        "async": "^3.2.4",
@@ -3084,7 +3088,6 @@
      "integrity": "sha512-bEL/yUb/fNNiNTuUz979Z0Yg5L+LzLxGJz8x79lYmR54fmTIb6ob/hNQgkQnIUDWIFjZVQwl9Xs356I6BAMHfw==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "glob": "^7.1.4",
        "graceful-fs": "^4.2.0",
@@ -3107,7 +3110,6 @@
      "integrity": "sha512-8p0AUk4XODgIewSi0l8Epjs+EVnWiK7NoDIEGU0HhE7+ZyY8D1IMY7odu5lRrFXGg71L15KG8QrPmum45RTtdA==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "core-util-is": "~1.0.0",
        "inherits": "~2.0.3",
@@ -3123,8 +3125,7 @@
      "resolved": "https://registry.npmmirror.com/safe-buffer/-/safe-buffer-5.1.2.tgz",
      "integrity": "sha512-Gd2UZBJDkXlY7GbJxfsE8/nvKkUEU1G38c1siN6QP6a9PT9MmHB8GnpscSmMJSoF8LOIrt8ud/wPtojys4G6+g==",
      "dev": true,
-      "license": "MIT",
-      "peer": true
+      "license": "MIT"
    },
    "node_modules/archiver-utils/node_modules/string_decoder": {
      "version": "1.1.1",
@@ -3132,7 +3133,6 @@
      "integrity": "sha512-n/ShnvDi6FHbbVfviro+WojiFzv+s8MPMHBczVePfUpDJLwoLT0ht1l4YwBCbi8pJAveEEdnkHyPyTP/mzRfwg==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "safe-buffer": "~5.1.0"
      }
@@ -3351,6 +3351,7 @@
        }
      ],
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "caniuse-lite": "^1.0.30001716",
        "electron-to-chromium": "^1.5.149",
@@ -3848,7 +3849,6 @@
      "integrity": "sha512-D3uMHtGc/fcO1Gt1/L7i1e33VOvD4A9hfQLP+6ewd+BvG/gQ84Yh4oftEhAdjSMgBgwGL+jsppT7JYNpo6MHHg==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "buffer-crc32": "^0.2.13",
        "crc32-stream": "^4.0.2",
@@ -3994,7 +3994,6 @@
      "integrity": "sha512-ROmzCKrTnOwybPcJApAA6WBWij23HVfGVNKqqrZpuyZOHqK2CwHSvpGuyt/UNNvaIjEd8X5IFGp4Mh+Ie1IHJQ==",
      "dev": true,
      "license": "Apache-2.0",
-      "peer": true,
      "bin": {
        "crc32": "bin/crc32.njs"
      },
@@ -4008,7 +4007,6 @@
      "integrity": "sha512-NT7w2JVU7DFroFdYkeq8cywxrgjPHWkdX1wjpRQXPX5Asews3tA+Ght6lddQO5Mkumffp3X7GEqku3epj2toIw==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "crc-32": "^1.2.0",
        "readable-stream": "^3.4.0"
@@ -4248,6 +4246,7 @@
      "integrity": "sha512-NoXo6Liy2heSklTI5OIZbCgXC1RzrDQsZkeEwXhdOro3FT1VBOvbubvscdPnjVuQ4AMwwv61oaH96AbiYg9EnQ==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "app-builder-lib": "25.1.8",
        "builder-util": "25.1.7",
@@ -4410,6 +4409,7 @@
      "integrity": "sha512-6dLslJrQYB1qvqVPYRv1PhAA/uytC66nUeiTcq2JXiBzrmTWCHppqtGUjZhvnSRVatBCT5/SFdizdzcBiEiYUg==",
      "hasInstallScript": true,
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "@electron/get": "^2.0.0",
        "@types/node": "^22.7.7",
@@ -4454,7 +4454,6 @@
      "integrity": "sha512-2ntkJ+9+0GFP6nAISiMabKt6eqBB0kX1QqHNWFWAXgi0VULKGisM46luRFpIBiU3u/TDmhZMM8tzvo2Abn3ayg==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "app-builder-lib": "25.1.8",
        "archiver": "^5.3.1",
@@ -4468,7 +4467,6 @@
      "integrity": "sha512-oRXApq54ETRj4eMiFzGnHWGy+zo5raudjuxN0b8H7s/RU2oW0Wvsx9O0ACRN/kRq9E8Vu/ReskGB5o3ji+FzHQ==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "graceful-fs": "^4.2.0",
        "jsonfile": "^6.0.1",
@@ -4484,7 +4482,6 @@
      "integrity": "sha512-5dgndWOriYSm5cnYaJNhalLNDKOqFwyDB/rr1E9ZsGciGvKPs8R2xYGCacuf3z6K1YKDz182fd+fY3cn3pMqXQ==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "universalify": "^2.0.0"
      },
@@ -4498,7 +4495,6 @@
      "integrity": "sha512-gptHNQghINnc/vTGIk0SOFGFNXw7JVrlRUtConJRlvaw6DuX0wO5Jeko9sWrMBhh+PsYAZ7oXAiOnf/UKogyiw==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "engines": {
        "node": ">= 10.0.0"
      }
@@ -4813,6 +4809,7 @@
      "integrity": "sha512-LSehfdpgMeWcTZkWZVIJl+tkZ2nuSkyyB9C27MZqFWXuph7DvaowgcTvKqxvpLW1JZIk8PN7hFY3Rj9LQ7m7lg==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "@eslint-community/eslint-utils": "^4.2.0",
        "@eslint-community/regexpp": "^4.12.1",
@@ -4874,6 +4871,7 @@
      "integrity": "sha512-zc1UmCpNltmVY34vuLRV61r1K27sWuX39E+uyUnY8xS2Bex88VV9cugG+UZbRSRGtGyFboj+D8JODyme1plMpw==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "bin": {
        "eslint-config-prettier": "bin/cli.js"
      },
@@ -5351,8 +5349,7 @@
      "resolved": "https://registry.npmmirror.com/fs-constants/-/fs-constants-1.0.0.tgz",
      "integrity": "sha512-y6OAwoSIf7FyjMIv94u+b5rdheZEjzR63GTyZJm5qh4Bi+2YgwLCcI/fPFZkL5PSixOt6ZNKm+w+Hfp/Bciwow==",
      "dev": true,
-      "license": "MIT",
-      "peer": true
+      "license": "MIT"
    },
    "node_modules/fs-extra": {
      "version": "8.1.0",
@@ -6108,8 +6105,7 @@
      "resolved": "https://registry.npmmirror.com/isarray/-/isarray-1.0.0.tgz",
      "integrity": "sha512-VLghIWNM6ELQzo7zwmcg0NmTVyWKYjvIeM83yjp0wRDTmUnrM678fQbcKBo6n2CJEF0szoG//ytg+TKla89ALQ==",
      "dev": true,
-      "license": "MIT",
-      "peer": true
+      "license": "MIT"
    },
    "node_modules/isbinaryfile": {
      "version": "5.0.4",
@@ -6300,7 +6296,6 @@
      "integrity": "sha512-b94GiNHQNy6JNTrt5w6zNyffMrNkXZb3KTkCZJb2V1xaEGCk093vkZ2jk3tpaeP33/OiXC+WvK9AxUebnf5nbw==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "readable-stream": "^2.0.5"
      },
@@ -6314,7 +6309,6 @@
      "integrity": "sha512-8p0AUk4XODgIewSi0l8Epjs+EVnWiK7NoDIEGU0HhE7+ZyY8D1IMY7odu5lRrFXGg71L15KG8QrPmum45RTtdA==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "core-util-is": "~1.0.0",
        "inherits": "~2.0.3",
@@ -6330,8 +6324,7 @@
      "resolved": "https://registry.npmmirror.com/safe-buffer/-/safe-buffer-5.1.2.tgz",
      "integrity": "sha512-Gd2UZBJDkXlY7GbJxfsE8/nvKkUEU1G38c1siN6QP6a9PT9MmHB8GnpscSmMJSoF8LOIrt8ud/wPtojys4G6+g==",
      "dev": true,
-      "license": "MIT",
-      "peer": true
+      "license": "MIT"
    },
    "node_modules/lazystream/node_modules/string_decoder": {
      "version": "1.1.1",
@@ -6339,7 +6332,6 @@
      "integrity": "sha512-n/ShnvDi6FHbbVfviro+WojiFzv+s8MPMHBczVePfUpDJLwoLT0ht1l4YwBCbi8pJAveEEdnkHyPyTP/mzRfwg==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "safe-buffer": "~5.1.0"
      }
@@ -6391,32 +6383,28 @@
      "resolved": "https://registry.npmmirror.com/lodash.defaults/-/lodash.defaults-4.2.0.tgz",
      "integrity": "sha512-qjxPLHd3r5DnsdGacqOMU6pb/avJzdh9tFX2ymgoZE27BmjXrNy/y4LoaiTeAb+O3gL8AfpJGtqfX/ae2leYYQ==",
      "dev": true,
-      "license": "MIT",
-      "peer": true
+      "license": "MIT"
    },
    "node_modules/lodash.difference": {
      "version": "4.5.0",
      "resolved": "https://registry.npmmirror.com/lodash.difference/-/lodash.difference-4.5.0.tgz",
      "integrity": "sha512-dS2j+W26TQ7taQBGN8Lbbq04ssV3emRw4NY58WErlTO29pIqS0HmoT5aJ9+TUQ1N3G+JOZSji4eugsWwGp9yPA==",
      "dev": true,
-      "license": "MIT",
-      "peer": true
+      "license": "MIT"
    },
    "node_modules/lodash.flatten": {
      "version": "4.4.0",
      "resolved": "https://registry.npmmirror.com/lodash.flatten/-/lodash.flatten-4.4.0.tgz",
      "integrity": "sha512-C5N2Z3DgnnKr0LOpv/hKCgKdb7ZZwafIrsesve6lmzvZIRZRGaZ/l6Q8+2W7NaT+ZwO3fFlSCzCzrDCFdJfZ4g==",
      "dev": true,
-      "license": "MIT",
-      "peer": true
+      "license": "MIT"
    },
    "node_modules/lodash.isplainobject": {
      "version": "4.0.6",
      "resolved": "https://registry.npmmirror.com/lodash.isplainobject/-/lodash.isplainobject-4.0.6.tgz",
      "integrity": "sha512-oSXzaWypCMHkPC3NvBEaPHf0KsA5mvPrOPgQWDsbg8n7orZ290M0BmC/jgRZ4vcJ6DTAhjrsSYgdsW/F+MFOBA==",
      "dev": true,
-      "license": "MIT",
-      "peer": true
+      "license": "MIT"
    },
    "node_modules/lodash.merge": {
      "version": "4.6.2",
@@ -6430,8 +6418,7 @@
      "resolved": "https://registry.npmmirror.com/lodash.union/-/lodash.union-4.6.0.tgz",
      "integrity": "sha512-c4pB2CdGrGdjMKYLA+XiRDO7Y0PRQbm/Gzg8qMj+QH+pFVAoTp5sBpO0odL3FjoPCGjK96p6qsP+yQoiLoOBcw==",
      "dev": true,
-      "license": "MIT",
-      "peer": true
+      "license": "MIT"
    },
    "node_modules/log-symbols": {
      "version": "4.1.0",
@@ -6984,7 +6971,6 @@
      "integrity": "sha512-6eZs5Ls3WtCisHWp9S2GUy8dqkpGi4BVSz3GaqiE6ezub0512ESztXUwUB6C6IKbQkY2Pnb/mD4WYojCRwcwLA==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "engines": {
        "node": ">=0.10.0"
      }
@@ -7408,6 +7394,7 @@
      "integrity": "sha512-QQtaxnoDJeAkDvDKWCLiwIXkTgRhwYDEQCghU9Z6q03iyek/rxRh/2lC3HB7P8sWT2xC/y5JDctPLBIGzHKbhw==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "bin": {
        "prettier": "bin/prettier.cjs"
      },
@@ -7436,8 +7423,7 @@
      "resolved": "https://registry.npmmirror.com/process-nextick-args/-/process-nextick-args-2.0.1.tgz",
      "integrity": "sha512-3ouUOpQhtgrbOa17J7+uxOTpITYWaGP7/AhoR3+A+/1e9skrzelGi/dXzEYyvbxubEF6Wn2ypscTKiKJFFn1ag==",
      "dev": true,
-      "license": "MIT",
-      "peer": true
+      "license": "MIT"
    },
    "node_modules/progress": {
      "version": "2.0.3",
@@ -7556,7 +7542,6 @@
      "integrity": "sha512-v05I2k7xN8zXvPD9N+z/uhXPaj0sUFCe2rcWZIpBsqxfP7xXFQ0tipAd/wjj1YxWyWtUS5IDJpOG82JKt2EAVA==",
      "dev": true,
      "license": "Apache-2.0",
-      "peer": true,
      "dependencies": {
        "minimatch": "^5.1.0"
      }
@@ -7567,7 +7552,6 @@
      "integrity": "sha512-lKwV/1brpG6mBUFHtb7NUmtABCb2WZZmm2wNiOA5hAb8VdCS4B3dtMWyvcoViccwAW/COERjXLt0zP1zXUN26g==",
      "dev": true,
      "license": "ISC",
-      "peer": true,
      "dependencies": {
        "brace-expansion": "^2.0.1"
      },
@@ -8235,7 +8219,6 @@
      "integrity": "sha512-ujeqbceABgwMZxEJnk2HDY2DlnUZ+9oEcb1KzTVfYHio0UE6dG71n60d8D2I4qNvleWrrXpmjpt7vZeF1LnMZQ==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "bl": "^4.0.3",
        "end-of-stream": "^1.4.1",
@@ -8360,6 +8343,7 @@
      "integrity": "sha512-M7BAV6Rlcy5u+m6oPhAPFgJTzAioX/6B0DxyvDlo9l8+T3nLKbrczg2WLUyzd45L8RqfUMyGPzekbMvX2Ldkwg==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "engines": {
        "node": ">=12"
      },
@@ -8462,6 +8446,7 @@
      "integrity": "sha512-p1diW6TqL9L07nNxvRMM7hMMw4c5XOo/1ibL4aAIGmSAt9slTE1Xgw5KWuof2uTOvCg9BY7ZRi+GaF+7sfgPeQ==",
      "devOptional": true,
      "license": "Apache-2.0",
+      "peer": true,
      "bin": {
        "tsc": "bin/tsc",
        "tsserver": "bin/tsserver"
@@ -8611,6 +8596,7 @@
      "integrity": "sha512-cZn6NDFE7wdTpINgs++ZJ4N49W2vRp8LCKrn3Ob1kYNtOo21vfDoaV5GzBfLU4MovSAB8uNRm4jgzVQZ+mBzPQ==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "esbuild": "^0.25.0",
        "fdir": "^6.4.4",
@@ -8701,6 +8687,7 @@
      "integrity": "sha512-M7BAV6Rlcy5u+m6oPhAPFgJTzAioX/6B0DxyvDlo9l8+T3nLKbrczg2WLUyzd45L8RqfUMyGPzekbMvX2Ldkwg==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "engines": {
        "node": ">=12"
      },
@@ -8720,6 +8707,7 @@
      "resolved": "https://registry.npmmirror.com/vue/-/vue-3.5.13.tgz",
      "integrity": "sha512-wmeiSMxkZCSc+PM2w2VRsOYAZC8GdipNFRTsLSfodVqI9mbejKeXEGr8SckuLnrQPGe3oJN5c3K0vpoU9q/wCQ==",
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "@vue/compiler-dom": "3.5.13",
        "@vue/compiler-sfc": "3.5.13",
@@ -8742,6 +8730,7 @@
      "integrity": "sha512-dbCBnd2e02dYWsXoqX5yKUZlOt+ExIpq7hmHKPb5ZqKcjf++Eo0hMseFTZMLKThrUk61m+Uv6A2YSBve6ZvuDQ==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "debug": "^4.4.0",
        "eslint-scope": "^8.2.0",
@@ -9046,7 +9035,6 @@
      "integrity": "sha512-9qv4rlDiopXg4E69k+vMHjNN63YFMe9sZMrdlvKnCjlCRWeCBswPPMPUfx+ipsAWq1LXHe70RcbaHdJJpS6hyQ==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "archiver-utils": "^3.0.4",
        "compress-commons": "^4.1.2",
@@ -9062,7 +9050,6 @@
      "integrity": "sha512-KVgf4XQVrTjhyWmx6cte4RxonPLR9onExufI1jhvw/MQ4BB6IsZD5gT8Lq+u/+pRkWna/6JoHpiQioaqFP5Rzw==",
      "dev": true,
      "license": "MIT",
-      "peer": true,
      "dependencies": {
        "glob": "^7.2.3",
        "graceful-fs": "^4.2.0",
--- a/src/main/types/index.ts
+++ b/src/main/types/index.ts
@@ -8,6 +8,8 @@ export interface Controls {
  targetLang: string,
  transModel: string,
  ollamaName: string,
+  ollamaUrl: string,
+  ollamaApiKey: string,
  engine: string,
  audio: 0 | 1,
  translation: boolean,
@@ -15,6 +17,9 @@ export interface Controls {
  API_KEY: string,
  voskModelPath: string,
  sosvModelPath: string,
+  glmUrl: string,
+  glmModel: string,
+  glmApiKey: string,
  recordingPath: string,
  customized: boolean,
  customizedApp: string,
--- a/src/main/utils/AllConfig.ts
+++ b/src/main/utils/AllConfig.ts
@@ -6,7 +6,7 @@ import { Log } from './Log'
 import { app, BrowserWindow } from 'electron'
 import * as path from 'path'
 import * as fs from 'fs'
-import os from 'os'
+import * as os from 'os'

 interface CaptionTranslation {
  time_s: string,
@@ -44,13 +44,18 @@ const defaultControls: Controls = {
  sourceLang: 'en',
  targetLang: 'zh',
  transModel: 'ollama',
-  ollamaName: '',
+  ollamaName: 'qwen2.5:0.5b',
+  ollamaUrl: 'http://localhost:11434',
+  ollamaApiKey: '',
  engine: 'gummy',
  audio: 0,
  engineEnabled: false,
  API_KEY: '',
  voskModelPath: '',
  sosvModelPath: '',
+  glmUrl: 'https://open.bigmodel.cn/api/paas/v4/audio/transcriptions',
+  glmModel: 'glm-asr-2512',
+  glmApiKey: '',
  recordingPath: getDesktopPath(),
  translation: true,
  recording: false,
--- a/src/main/utils/CaptionEngine.ts
+++ b/src/main/utils/CaptionEngine.ts
@@ -1,8 +1,8 @@
 import { exec, spawn } from 'child_process'
 import { app } from 'electron'
 import { is } from '@electron-toolkit/utils'
-import path from 'path'
-import net from 'net'
+import * as path from 'path'
+import * as net from 'net'
 import { controlWindow } from '../ControlWindow'
 import { allConfig } from './AllConfig'
 import { i18n } from '../i18n'
@@ -60,7 +60,7 @@ export class CaptionEngine {
          this.appPath = path.join(process.resourcesPath, 'engine', 'main.exe')
        }
        else {
-          this.appPath = path.join(process.resourcesPath, 'engine', 'main')
+          this.appPath = path.join(process.resourcesPath, 'engine', 'main', 'main')
        }
      }
      this.command.push('-a', allConfig.controls.audio ? '1' : '0')
@@ -87,6 +87,8 @@ export class CaptionEngine {
        this.command.push('-vosk', `"${allConfig.controls.voskModelPath}"`)
        this.command.push('-tm', allConfig.controls.transModel)
        this.command.push('-omn', allConfig.controls.ollamaName)
+        if(allConfig.controls.ollamaUrl) this.command.push('-ourl', allConfig.controls.ollamaUrl)
+        if(allConfig.controls.ollamaApiKey) this.command.push('-okey', allConfig.controls.ollamaApiKey)
      }
      else if(allConfig.controls.engine === 'sosv'){
        this.command.push('-e', 'sosv')
@@ -94,10 +96,25 @@ export class CaptionEngine {
        this.command.push('-sosv', `"${allConfig.controls.sosvModelPath}"`)
        this.command.push('-tm', allConfig.controls.transModel)
        this.command.push('-omn', allConfig.controls.ollamaName)
+        if(allConfig.controls.ollamaUrl) this.command.push('-ourl', allConfig.controls.ollamaUrl)
+        if(allConfig.controls.ollamaApiKey) this.command.push('-okey', allConfig.controls.ollamaApiKey)
+      }
+      else if(allConfig.controls.engine === 'glm'){
+        this.command.push('-e', 'glm')
+        this.command.push('-s', allConfig.controls.sourceLang)
+        this.command.push('-gurl', allConfig.controls.glmUrl)
+        this.command.push('-gmodel', allConfig.controls.glmModel)
+        if(allConfig.controls.glmApiKey) {
+          this.command.push('-gkey', allConfig.controls.glmApiKey)
+        }
+        this.command.push('-tm', allConfig.controls.transModel)
+        this.command.push('-omn', allConfig.controls.ollamaName)
+        if(allConfig.controls.ollamaUrl) this.command.push('-ourl', allConfig.controls.ollamaUrl)
+        if(allConfig.controls.ollamaApiKey) this.command.push('-okey', allConfig.controls.ollamaApiKey)
      }
    }
    Log.info('Engine Path:', this.appPath)
-    if(this.command.length > 2 && this.command.at(-2) === '-k') {
+    if(this.command.length > 2 && this.command[this.command.length - 2] === '-k') {
      const _command = [...this.command]
      _command[_command.length -1] = _command[_command.length -1].replace(/./g, '*')
      Log.info('Engine Command:', _command)
--- a/src/renderer/src/components/EngineControl.vue
+++ b/src/renderer/src/components/EngineControl.vue
@@ -52,6 +52,44 @@
        v-model:value="currentOllamaName"
      ></a-input>
    </div>
+    <div class="input-item" v-if="transModel && currentTransModel === 'ollama'">
+      <span class="input-label">Ollama Domain</span>
+      <a-input
+        class="input-area"
+        v-model:value="currentOllamaUrl"
+        placeholder="http://localhost:11434"
+      ></a-input>
+    </div>
+    <div class="input-item" v-if="transModel && currentTransModel === 'ollama'">
+      <span class="input-label">Ollama API Key</span>
+      <a-input-password
+        class="input-area"
+        v-model:value="currentOllamaApiKey"
+      ></a-input-password>
+    </div>
+    <div class="input-item" v-if="currentEngine === 'glm'">
+      <span class="input-label">GLM API URL</span>
+      <a-input
+        class="input-area"
+        v-model:value="currentGlmUrl"
+        placeholder="https://open.bigmodel.cn/api/paas/v4/audio/transcriptions"
+      ></a-input>
+    </div>
+    <div class="input-item" v-if="currentEngine === 'glm'">
+      <span class="input-label">GLM Model Name</span>
+      <a-input
+        class="input-area"
+        v-model:value="currentGlmModel"
+        placeholder="glm-asr-2512"
+      ></a-input>
+    </div>
+    <div class="input-item" v-if="currentEngine === 'glm'">
+      <span class="input-label">GLM API Key</span>
+      <a-input-password
+        class="input-area"
+        v-model:value="currentGlmApiKey"
+      ></a-input-password>
+    </div>
    <div class="input-item">
      <span class="input-label">{{ $t('engine.audioType') }}</span>
      <a-select
@@ -239,9 +277,14 @@ const currentTranslation = ref<boolean>(true)
 const currentRecording = ref<boolean>(false)
 const currentTransModel = ref('ollama')
 const currentOllamaName = ref('')
+const currentOllamaUrl = ref('')
+const currentOllamaApiKey = ref('')
 const currentAPI_KEY = ref<string>('')
 const currentVoskModelPath = ref<string>('')
 const currentSosvModelPath = ref<string>('')
+const currentGlmUrl = ref<string>('')
+const currentGlmModel = ref<string>('')
+const currentGlmApiKey = ref<string>('')
 const currentRecordingPath = ref<string>('')
 const currentCustomized = ref<boolean>(false)
 const currentCustomizedApp = ref('')
@@ -294,12 +337,17 @@ function applyChange(){
  engineControl.transModel = currentTransModel.value
  engineControl.ollamaName = currentOllamaName.value
  engineControl.engine = currentEngine.value
+  engineControl.ollamaUrl = currentOllamaUrl.value ?? "http://localhost:11434"
+  engineControl.ollamaApiKey = currentOllamaApiKey.value
  engineControl.audio = currentAudio.value
  engineControl.translation = currentTranslation.value
  engineControl.recording = currentRecording.value
  engineControl.API_KEY = currentAPI_KEY.value
  engineControl.voskModelPath = currentVoskModelPath.value
  engineControl.sosvModelPath = currentSosvModelPath.value
+  engineControl.glmUrl = currentGlmUrl.value ?? "https://open.bigmodel.cn/api/paas/v4/audio/transcriptions"
+  engineControl.glmModel = currentGlmModel.value ?? "glm-asr-2512"
+  engineControl.glmApiKey = currentGlmApiKey.value
  engineControl.recordingPath = currentRecordingPath.value
  engineControl.customized = currentCustomized.value
  engineControl.customizedApp = currentCustomizedApp.value
@@ -320,6 +368,8 @@ function cancelChange(){
  currentTargetLang.value = engineControl.targetLang
  currentTransModel.value = engineControl.transModel
  currentOllamaName.value = engineControl.ollamaName
+  currentOllamaUrl.value = engineControl.ollamaUrl
+  currentOllamaApiKey.value = engineControl.ollamaApiKey
  currentEngine.value = engineControl.engine
  currentAudio.value = engineControl.audio
  currentTranslation.value = engineControl.translation
@@ -327,6 +377,9 @@ function cancelChange(){
  currentAPI_KEY.value = engineControl.API_KEY
  currentVoskModelPath.value = engineControl.voskModelPath
  currentSosvModelPath.value = engineControl.sosvModelPath
+  currentGlmUrl.value = engineControl.glmUrl
+  currentGlmModel.value = engineControl.glmModel
+  currentGlmApiKey.value = engineControl.glmApiKey
  currentRecordingPath.value = engineControl.recordingPath
  currentCustomized.value = engineControl.customized
  currentCustomizedApp.value = engineControl.customizedApp
--- a/src/renderer/src/i18n/config/engine.ts
+++ b/src/renderer/src/i18n/config/engine.ts
@@ -58,6 +58,21 @@ export const engines = {
        { value: 'ollama', label: 'Ollama 本地模型' },
        { value: 'google', label: 'Google API 调用' },
      ]
+    },
+    {
+      value: 'glm',
+      label: '云端 / 智谱AI / GLM-ASR',
+      languages: [
+        { value: 'auto', type: -1, label: '自动检测' },
+        { value: 'en', type: 0, label: '英语' },
+        { value: 'zh', type: 0, label: '中文' },
+        { value: 'ja', type: 0, label: '日语' },
+        { value: 'ko', type: 0, label: '韩语' },
+      ],
+      transModel: [
+        { value: 'ollama', label: 'Ollama 本地模型' },
+        { value: 'google', label: 'Google API 调用' },
+      ]
    }
  ],
  en: [
@@ -118,6 +133,21 @@ export const engines = {
        { value: 'ollama', label: 'Ollama Local Model' },
        { value: 'google', label: 'Google API Call' },
      ]
+    },
+    {
+      value: 'glm',
+      label: 'Cloud / Zhipu AI / GLM-ASR',
+      languages: [
+        { value: 'auto', type: -1, label: 'Auto Detect' },
+        { value: 'en', type: 0, label: 'English' },
+        { value: 'zh', type: 0, label: 'Chinese' },
+        { value: 'ja', type: 0, label: 'Japanese' },
+        { value: 'ko', type: 0, label: 'Korean' },
+      ],
+      transModel: [
+        { value: 'ollama', label: 'Ollama Local Model' },
+        { value: 'google', label: 'Google API Call' },
+      ]
    }
  ],
  ja: [
@@ -178,6 +208,21 @@ export const engines = {
        { value: 'ollama', label: 'Ollama ローカルモデル' },
        { value: 'google', label: 'Google API 呼び出し' },
      ]
+    },
+    {
+      value: 'glm',
+      label: 'クラウド / 智譜AI / GLM-ASR',
+      languages: [
+        { value: 'auto', type: -1, label: '自動検出' },
+        { value: 'en', type: 0, label: '英語' },
+        { value: 'zh', type: 0, label: '中国語' },
+        { value: 'ja', type: 0, label: '日本語' },
+        { value: 'ko', type: 0, label: '韓国語' },
+      ],
+      transModel: [
+        { value: 'ollama', label: 'Ollama ローカルモデル' },
+        { value: 'google', label: 'Google API 呼び出し' },
+      ]
    }
  ]
 }
--- a/src/renderer/src/stores/engineControl.ts
+++ b/src/renderer/src/stores/engineControl.ts
@@ -21,6 +21,8 @@ export const useEngineControlStore = defineStore('engineControl', () => {
  const targetLang = ref<string>('zh')
  const transModel = ref<string>('ollama')
  const ollamaName = ref<string>('')
+  const ollamaUrl = ref<string>('')
+  const ollamaApiKey = ref<string>('')
  const engine = ref<string>('gummy')
  const audio = ref<0 | 1>(0)
  const translation = ref<boolean>(true)
@@ -28,6 +30,9 @@ export const useEngineControlStore = defineStore('engineControl', () => {
  const API_KEY = ref<string>('')
  const voskModelPath = ref<string>('')
  const sosvModelPath = ref<string>('')
+  const glmUrl = ref<string>('https://open.bigmodel.cn/api/paas/v4/audio/transcriptions')
+  const glmModel = ref<string>('glm-asr-2512')
+  const glmApiKey = ref<string>('')
  const recordingPath = ref<string>('')
  const customized = ref<boolean>(false)
  const customizedApp = ref<string>('')
@@ -44,6 +49,8 @@ export const useEngineControlStore = defineStore('engineControl', () => {
      targetLang: targetLang.value,
      transModel: transModel.value,
      ollamaName: ollamaName.value,
+      ollamaUrl: ollamaUrl.value,
+      ollamaApiKey: ollamaApiKey.value,
      engine: engine.value,
      audio: audio.value,
      translation: translation.value,
@@ -51,6 +58,9 @@ export const useEngineControlStore = defineStore('engineControl', () => {
      API_KEY: API_KEY.value,
      voskModelPath: voskModelPath.value,
      sosvModelPath: sosvModelPath.value,
+      glmUrl: glmUrl.value,
+      glmModel: glmModel.value,
+      glmApiKey: glmApiKey.value,
      recordingPath: recordingPath.value,
      customized: customized.value,
      customizedApp: customizedApp.value,
@@ -80,6 +90,8 @@ export const useEngineControlStore = defineStore('engineControl', () => {
    targetLang.value = controls.targetLang
    transModel.value = controls.transModel
    ollamaName.value = controls.ollamaName
+    ollamaUrl.value = controls.ollamaUrl
+    ollamaApiKey.value = controls.ollamaApiKey
    engine.value = controls.engine
    audio.value = controls.audio
    engineEnabled.value = controls.engineEnabled
@@ -88,6 +100,9 @@ export const useEngineControlStore = defineStore('engineControl', () => {
    API_KEY.value = controls.API_KEY
    voskModelPath.value = controls.voskModelPath
    sosvModelPath.value = controls.sosvModelPath
+    glmUrl.value = controls.glmUrl || 'https://open.bigmodel.cn/api/paas/v4/audio/transcriptions'
+    glmModel.value = controls.glmModel || 'glm-asr-2512'
+    glmApiKey.value = controls.glmApiKey
    recordingPath.value = controls.recordingPath
    customized.value = controls.customized
    customizedApp.value = controls.customizedApp
@@ -150,6 +165,8 @@ export const useEngineControlStore = defineStore('engineControl', () => {
    targetLang,         // 目标语言
    transModel,         // 翻译模型
    ollamaName,         // Ollama 模型
+    ollamaUrl,
+    ollamaApiKey,
    engine,             // 字幕引擎
    audio,              // 选择音频
    translation,        // 是否启用翻译
@@ -157,6 +174,9 @@ export const useEngineControlStore = defineStore('engineControl', () => {
    API_KEY,            // API KEY
    voskModelPath,      // vosk 模型路径
    sosvModelPath,      // sosv 模型路径
+    glmUrl,             // GLM API URL
+    glmModel,           // GLM 模型名称
+    glmApiKey,          // GLM API Key
    recordingPath,      // 录音保存路径
    customized,         // 是否使用自定义字幕引擎
    customizedApp,      // 自定义字幕引擎的应用程序
--- a/src/renderer/src/types/index.ts
+++ b/src/renderer/src/types/index.ts
@@ -8,6 +8,8 @@ export interface Controls {
  targetLang: string,
  transModel: string,
  ollamaName: string,
+  ollamaUrl: string,
+  ollamaApiKey: string,
  engine: string,
  audio: 0 | 1,
  translation: boolean,
@@ -15,6 +17,9 @@ export interface Controls {
  API_KEY: string,
  voskModelPath: string,
  sosvModelPath: string,
+  glmUrl: string,
+  glmModel: string,
+  glmApiKey: string,
  recordingPath: string,
  customized: boolean,
  customizedApp: string,