Instructions to use MoYoYoTech/VoiceDialogue with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MoYoYoTech/VoiceDialogue with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-to-speech", model="MoYoYoTech/VoiceDialogue")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MoYoYoTech/VoiceDialogue", dtype="auto")

llama-cpp-python

How to use MoYoYoTech/VoiceDialogue with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MoYoYoTech/VoiceDialogue",
	filename="assets/models/llm/qwen/Qwen3-8B-Q6_K.gguf",
)

llm.create_chat_completion(
	messages = "\"The answer to the universe is 42\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use MoYoYoTech/VoiceDialogue with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MoYoYoTech/VoiceDialogue:Q6_K
# Run inference directly in the terminal:
llama-cli -hf MoYoYoTech/VoiceDialogue:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MoYoYoTech/VoiceDialogue:Q6_K
# Run inference directly in the terminal:
llama-cli -hf MoYoYoTech/VoiceDialogue:Q6_K

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf MoYoYoTech/VoiceDialogue:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf MoYoYoTech/VoiceDialogue:Q6_K

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf MoYoYoTech/VoiceDialogue:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MoYoYoTech/VoiceDialogue:Q6_K

Use Docker

docker model run hf.co/MoYoYoTech/VoiceDialogue:Q6_K

LM Studio
Jan
Ollama
How to use MoYoYoTech/VoiceDialogue with Ollama:
```
ollama run hf.co/MoYoYoTech/VoiceDialogue:Q6_K
```

Unsloth Studio new

How to use MoYoYoTech/VoiceDialogue with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for MoYoYoTech/VoiceDialogue to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for MoYoYoTech/VoiceDialogue to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MoYoYoTech/VoiceDialogue to start chatting

Pi new

How to use MoYoYoTech/VoiceDialogue with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf MoYoYoTech/VoiceDialogue:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "MoYoYoTech/VoiceDialogue:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use MoYoYoTech/VoiceDialogue with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf MoYoYoTech/VoiceDialogue:Q6_K

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default MoYoYoTech/VoiceDialogue:Q6_K

Run Hermes

hermes

Docker Model Runner
How to use MoYoYoTech/VoiceDialogue with Docker Model Runner:
```
docker model run hf.co/MoYoYoTech/VoiceDialogue:Q6_K
```

Lemonade

How to use MoYoYoTech/VoiceDialogue with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MoYoYoTech/VoiceDialogue:Q6_K

Run and chat with the model

lemonade run user.VoiceDialogue-Q6_K

List all available models

lemonade list

liumaolin commited on Jul 4, 2025

Commit

15891ec

1 Parent(s): 5ecb408

Refactor SpeechMonitor to use active audio frame duration instead of count

Browse files

- Replace `active_audio_frame_count` with `active_audio_frame_duration` for more precise threshold control.
- Adjust `ACTIVE_FRAME_THRESHOLD` and associated calculations to use duration-based logic.

Files changed (1) hide show

src/voice_dialogue/services/speech/monitor.py +6 -5

src/voice_dialogue/services/speech/monitor.py CHANGED Viewed

@@ -26,10 +26,10 @@ from voice_dialogue.utils.logger import logger
 class SpeechMonitorConfig:
     """语音监控配置类"""
     MIN_AUDIO_AMPLITUDE = 0.01  # 最小音频振幅阈值
-    ACTIVE_FRAME_THRESHOLD = 10  # 连续活跃帧数阈值
     QUEUE_TIMEOUT = 0.1  # 队列获取超时时间（秒）
     # 时间阈值（毫秒）
     USER_SILENCE_THRESHOLD = 1 * 1000  # 用户静音阈值
     SILENCE_THRESHOLD = 0.3 * 1000  # 静音检测阈值
     AUDIO_FRAMES_THRESHOLD = 5 * 1000  # 音频帧时长阈值
@@ -80,7 +80,7 @@ class SpeechStateMonitor(BaseThread):
     def _reset_monitoring_state(self):
         """重置监控状态"""
         self.silence_audio_frame_count = 0
-        self.active_audio_frame_count = 0
         self.user_silence_duration = 0
         self.task_id = None
@@ -148,10 +148,11 @@ class SpeechStateMonitor(BaseThread):
         # 重置静音计时
         self.user_silence_duration = 0
-        self.active_audio_frame_count += 1
         # 检查是否需要中断当前任务
-        if self.active_audio_frame_count > self.config.ACTIVE_FRAME_THRESHOLD:
             voice_state_manager.interrupt_task_id = self.task_id
         return True
@@ -169,7 +170,7 @@ class SpeechStateMonitor(BaseThread):
         Returns:
             tuple: (更新后的音频帧缓存, 是否需要继续处理)
         """
-        self.active_audio_frame_count = 0
         duration = self._calculate_frame_duration_ms(audio_frame)
         if is_audio_frames_empty:

 class SpeechMonitorConfig:
     """语音监控配置类"""
     MIN_AUDIO_AMPLITUDE = 0.01  # 最小音频振幅阈值
     QUEUE_TIMEOUT = 0.1  # 队列获取超时时间（秒）
     # 时间阈值（毫秒）
+    ACTIVE_FRAME_THRESHOLD = 0.32 * 1000  # 连续活跃帧数阈值
     USER_SILENCE_THRESHOLD = 1 * 1000  # 用户静音阈值
     SILENCE_THRESHOLD = 0.3 * 1000  # 静音检测阈值
     AUDIO_FRAMES_THRESHOLD = 5 * 1000  # 音频帧时长阈值
     def _reset_monitoring_state(self):
         """重置监控状态"""
         self.silence_audio_frame_count = 0
+        self.active_audio_frame_duration = 0
         self.user_silence_duration = 0
         self.task_id = None
         # 重置静音计时
         self.user_silence_duration = 0
+        duration = self._calculate_frame_duration_ms(audio_frame)
+        self.active_audio_frame_duration += duration
         # 检查是否需要中断当前任务
+        if self.active_audio_frame_duration > self.config.ACTIVE_FRAME_THRESHOLD:
             voice_state_manager.interrupt_task_id = self.task_id
         return True
         Returns:
             tuple: (更新后的音频帧缓存, 是否需要继续处理)
         """
+        self.active_audio_frame_duration = 0
         duration = self._calculate_frame_duration_ms(audio_frame)
         if is_audio_frames_empty: