brew install ffmpeg
uv sync
uv run python -m camoufox fetch

uv run start

uv run start --http

export M365_ENTRY_URL='https://outlook.cloud.microsoft/host/xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/entity1-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx'
export SHAREPOINT_HOME_URL='https://tenant.sharepoint.com/sites/site_name'

# The storage location for input files
export SHAREPOINT_UPLOAD_FOLDER='Upload'

# The storage location for model output files
export SHAREPOINT_DOWNLOAD_FOLDER='Download'

# Restore the last locally stored browser conversation.
export VOICE_EDGE_RESTORE_LAST_CONVERSATION=1

# Disable local conversation persistence.
export VOICE_EDGE_DISABLE_CONVERSATION_PERSISTENCE=1

# Unified browser-provider state file.
export VOICE_EDGE_BROWSER_STATE_PATH="$HOME/.voice-edge/browser-provider-state.json"

export XIAOAI_ENABLED=1
export MI_USER='your_xiaomi_account'
export MI_PASS='your_password'
export XIAOAI_HARDWARE='LX01'
export MI_DID=''
export XIAOAI_OTP_FILE="$HOME/.mi.otp"
export XIAOAI_OTP_TIMEOUT=300
export XIAOAI_OTP_POLL_INTERVAL=0.5
export XIAOAI_WAKEUP_MODE='directive'

# Doubao
export XIAOAI_MODEL='LLM:doubao'
export DOUBAO_BROWSER_ENGINE='camoufox'

# Qwen
export XIAOAI_MODEL='LLM:qwen'
export QWEN_BROWSER_MODEL='qwen3.7-plus'

# DeepSeek
export XIAOAI_MODEL='LLM:deepseek'

# Microsoft 365 Copilot example
export XIAOAI_MODEL='LLM:m365-chatgpt-5.6'

export XIAOAI_SYSTEM_PROMPT='Please keep your answer concise and output text suitable for voice reading only.'
export XIAOAI_MAX_TOKENS=500
export XIAOAI_TEMPERATURE=0.3

export XIAOAI_TRIGGER_WITHOUT_KEYWORD=1
export XIAOAI_KEYWORDS='help me,please'
export XIAOAI_STOP_PHRASES='stop answering,stop,hold on'
export XIAOAI_NEW_CONVERSATION='Change the subject,new conversation,new chat,clear context,change the topic,start over'

export XIAOAI_NATIVE_KEYWORDS='weather,time'
export XIAOAI_NATIVE_STATUS_POLL_INTERVAL=0.25
export XIAOAI_NATIVE_PLAY_START_TIMEOUT=3.0
export XIAOAI_NATIVE_PLAY_END_TIMEOUT=30.0
export XIAOAI_NATIVE_IDLE_CONFIRMATIONS=1
export XIAOAI_NATIVE_STATUS_FALLBACK_DELAY=3.0
export XIAOAI_NATIVE_TAIL_GUARD=0.20

export XIAOAI_VOICE='zh'
export XIAOAI_TTS_SPEED=1.0
export XIAOAI_AUDIO_BIND_HOST='0.0.0.0'
export XIAOAI_AUDIO_PORT=8050
export XIAOAI_AUDIO_PUBLIC_HOST=''
export XIAOAI_PLAYBACK_DRAIN_MARGIN=0.25
export XIAOAI_PLAYBACK_DRAIN_MAX=180
export XIAOAI_PLAYBACK_STATUS_POLL_INTERVAL=0.15
export XIAOAI_PLAYBACK_STATUS_MAX_WAIT=4.0
export XIAOAI_PLAYBACK_IDLE_CONFIRMATIONS=1
export XIAOAI_PLAYBACK_TAIL_GUARD=0.20
export XIAOAI_PLAYBACK_TIMEOUT=300

export XIAOAI_POLL_INTERVAL=0.1
export XIAOAI_POLL_MIN_INTERVAL=0.08
export XIAOAI_POLL_LOG_EVERY=1
export XIAOAI_AUDIO_MAX_BUFFER_BYTES=524288
export XIAOAI_SPEECH_TARGET_CHARS=42
export XIAOAI_HISTORY_TURNS=6
export XIAOAI_MP3_BITRATE='64k'
export XIAOAI_QUERY_DEBOUNCE_SECONDS=4
export XIAOAI_WAKEUP_SUPPRESS_SECONDS=0

export TAVILY_API_KEY='your_api_key'
export XIAOAI_TAVILY_TOOL_ENABLED=1
export XIAOAI_TAVILY_TOOL_MAX_RESULTS=3
export XIAOAI_TAVILY_TOOL_TIMEOUT=30

uv run start --mi-list

export XIAOAI_LOCAL_DEVICES = '[
  {
    "name": "living-room",
    "ip": "192.168.1.101",
    "token": "",
    "hardware": "LX01",
    "mi_did": "",
    "audio_port": 8050
  },
  {
    "name": "bedroom",
    "ip": "192.168.1.102",
    "token": "",
    "hardware": "LX01",
    "mi_did": "",
    "audio_port": 8051
  }
]'

export VE_VOICE_CHAT_ENABLED=1
export VE_VOICE_CHAT_MODEL_DIR='/path/to/sherpa-onnx-kws-zipformer-zh-en-3M-2025-12-20'
export VE_VOICE_CHAT_ALIAS_DEEPSEEK='DeepSeek'
export VE_VOICE_CHAT_ALIAS_DOUBAO='Doubao'
export VE_VOICE_CHAT_HISTORY_CHAR_BUDGET=6000
export VE_VOICE_CHAT_SHOW_HUD=0
export VE_VOICE_CHAT_KWS_ENGINE='apple'
export SPEECH_HELPER_ON_DEVICE=1
export VE_VOICE_CHAT_CAPTURE_LOCALES='zh-CN,en-US'

# Single source of truth for wake-up configuration. Each entry defines only one primary keyword; aliases belong exclusively to that keyword.
# command_locale=None indicates that subsequent commands automatically use the first locale that returns valid text.
VE_VOICE_CHAT_WAKE_CONFIG = (
    {
        "keyword": "hello deepseek",
        "aliases": (
            "hello ts",
            "hello ds",
            "hello deep",
            "hello deepa",
            "hello deepak",
            "hello deepa sick",
        ),
        "route": ("model", "LLM:deepseek"),
        "command_locale": "en-US",
        "model_alias": os.getenv("VE_VOICE_CHAT_ALIAS_DEEPSEEK", "DeepSeek"),
        "score": None,
        "threshold": None,
        "apple_threshold": 0.88,
    },
    {
        "keyword": "Hello doubao",
        "aliases": ("Hello baozi",),
        "route": ("model", "LLM:doubao"),
        "command_locale": "en-US",
        "model_alias": os.getenv("VE_VOICE_CHAT_ALIAS_DOUBAO", "豆包"),
        "score": None,
        "threshold": None,
        "apple_threshold": 0.88,
    },
    {
        "keyword": "Change the subject",
        "aliases": (),
        "route": ("command", "new_session"),
        "command_locale": "en-US",
        "model_alias": None,
        "score": None,
        "threshold": None,
        "apple_threshold": 0.88,
    },
)

experimental:
  readResponseTTSServer:
    mcpId: "local-tts"
    toolName: "speak"
models:
  - name: Local
    provider: Local
    model: AUTODETECT
    apiBase: http://localhost:5000/v1/
    roles:
      - chat
    capabilities:
      - tool_use
  - name: LLM:m365-claude-opus
    provider: Local
    model: LLM:m365-claude-opus
    apiBase: http://localhost:5000/v1/
    roles:
      - chat
    defaultCompletionOptions:
      contextLength: 1000000
      maxTokens: 128000
    capabilities:
      - tool_use
      - image_input
    excludeToolOutputsFromTokenCount: true
  - name: LLM:m365-chatgpt-5.6
    provider: Local
    model: LLM:m365-chatgpt-5.6
    apiBase: http://localhost:5000/v1/
    roles:
      - chat
    defaultCompletionOptions:
      contextLength: 1050000
      maxTokens: 128000
    capabilities:
      - tool_use
      - image_input
    excludeToolOutputsFromTokenCount: true
  - name: embed:jina-v5
    provider: Local
    model: embed:jina-v5
    apiBase: http://localhost:5000/v1/
    roles:
      - embed
  - name: rerank:jina-v3
    provider: Local
    model: embed:jina-v3
    apiBase: http://localhost:5000/v1/
    roles:
      - rerank
  - name: FIM:qwen-2.5-coder-1.5B
    provider: Local
    model: FIM:qwen-2.5-coder-1.5B
    apiBase: http://localhost:5000/v1/
    roles:
      - edit
      - apply
      - autocomplete
  - name: FIM:qwen-2.5-coder-7B
    provider: Local
    model: FIM:qwen-2.5-coder-7B
    apiBase: http://localhost:5000/v1/
    roles:
      - edit
      - apply
      - autocomplete

  XiaoAI / OpenAI / MCP / Hotkeys / Voice Chat
                |
                v
        Voice Edge Core
                |
     +----------+----------+
     |          |          |
     v          v          v
    STT      Local LLM    Tools
     |          |          |
     +----------+----------+
                |
                v
      Conversation Engine
                |
                v
          Streaming TTS
                |
                v
   Local Audio / XiaoAI Audio

export VE_DOUBAO_LOG_DEBUG=1
export VE_QWEN_LOG_DEBUG=1
export VE_DEEPSEEK_LOG_DEBUG=1
export VE_DEEPSEEK_LOG_STREAM_CHUNKS=1
export VE_M365_LOG_DEBUG=1
export VE_M365_LOG_RELAY_TRACE=1
export VE_M365_LOG_ATTACHMENT=1