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")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MoYoYoTech/VoiceDialogue", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use MoYoYoTech/VoiceDialogue with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -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 serve -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 Desktop

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 serve -hf MoYoYoTech/VoiceDialogue:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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

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

Hermes Agent

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 serve -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

Atomic Chat

OpenClaw

How to use MoYoYoTech/VoiceDialogue with OpenClaw:

Start the llama.cpp server

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

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "MoYoYoTech/VoiceDialogue:Q6_K" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

VoiceDialogue / src

Commit History

Jun 12

04:40
Bundle Qwen3-ASR weights in packaged app; slim PyInstaller assets⁠

hzeng412 +1: Claude Fable 5

2e4bd5d

Jun 11

20:55
ASR: use auto language detection to reject non-speech (fixes hallucination)⁠

hzeng412 +1: Claude Fable 5

21dbad4

Jun 10

20:09
Make Qwen3-ASR the default on main; bump to 1.2.0⁠

hzeng412 +1: Claude Fable 5

3c70498
20:02
Add audio output device (speaker) selection⁠

hzeng412 +1: Claude Fable 5

a3bf559
19:50
Show the active ASR engine in the UI⁠

hzeng412 +1: Claude Fable 5

c3f5082
05:12
Fix websocket route registration for starlette >= 1.0⁠

hzeng412 +1: Claude Fable 5

a17b420
05:05
ASR: add Qwen3-ASR engine, default zh/en to it on this branch⁠

hzeng412 +1: Claude Fable 5

417ffa1

Jun 9

19:48
Add external mic array support, UI i18n, glass settings redesign, and fixes⁠

hzeng412 +1: Claude Opus 4.8 (1M context)

afd6c89

Jul 24, 2025

08:41
refactor(core): Architecturally decouple Audio, ASR, and TTS modules⁠

liumaolin

60f8238

Jul 23, 2025

07:58
简化LLM模型路径管理。

liumaolin

2baeba2

Jul 16, 2025

07:51
为LLMResponseGenerator类添加TaskStatusMixin混入，以增强任务有效性检查功能，确保在生成回答时任务状态的有效性。

liumaolin

d205383

Jul 15, 2025

08:39
更新音频任务处理逻辑，使用模型副本替代原始任务对象，以确保数据一致性和完整性。

liumaolin

2c7e742
08:14
重构处理LLM生成chunk内容的方法，以提高文本生成的准确性。

liumaolin

e3d17e2
03:01
去除对 LLM 输出的处理

liumaolin

08fc60d

Jul 14, 2025

02:49
更新LLM模型参数，调整top_p值为0.8，并添加max_tokens参数，设置为32768。

liumaolin

c531bfc
02:40
更新用户配置文件，修复logger导入路径以确保正确加载日志记录功能。

liumaolin

bbf79f2

Jul 11, 2025

06:41
添加获取TTS模型参考音频的API路由，支持通过模型ID获取音频文件。

liumaolin

226effc

Jul 10, 2025

08:46
更新API文档

liumaolin

5258538
08:41
缓存user_prompts以提高性能

liumaolin

d12af4f
08:37
调整prompt的逻辑，确保展示的提示词中不包含/no_think指令

liumaolin

22a06c4
08:15
添加设置相关的API路由⁠

liumaolin

15ab478
08:00
调整LLM prompt的存放位置

liumaolin

310c0ba
07:36
增强任务有效性检查，添加日志记录以便于调试。

liumaolin

b7ae839
07:22
在生成TTS音频时始终记录生成信息。

liumaolin

3a6b6fc
07:13
在`SpeechStateMonitor`类的初始化过程中调用该方法，确保在创建新语音任务时中断任务ID被正确重置。

liumaolin

259c23b

Jul 9, 2025

02:37
修复`PerformanceLogMixin`中的音频记录逻辑⁠

liumaolin

9bda9f9
02:30
修复`PerformanceLogMixin`中的调试模式检查逻辑⁠

liumaolin

8486c53
02:22
增强性能日志记录功能，新增用户问题日志记录方法⁠

liumaolin

7cddb77
02:22
Revise `ACTIVE_FRAME_THRESHOLD` from 0.32s to 0.1s

liumaolin

d662661

Jul 7, 2025

08:34
更新MoYoYo语音模型配置，修改文本分割方法并新增角色模型⁠

liumaolin

46eb532
07:23
更新MoYoYo语音模型配置，新增优先级字段⁠

liumaolin

efefd3d
06:36
新增Mixin类以增强语音任务处理功能⁠

liumaolin

2ebe57f
04:00
添加MoYoYo语音模型“白岩松”及相关文件⁠

liumaolin

d74bcbf

Jul 6, 2025

02:08
重构`is_task_interrupted`方法以检查语音任务中断状态⁠

liumaolin

02c321c

Jul 4, 2025

08:44
Add `has_no_words` check to skip punctuation-only TTS tasks and enhance debug logs⁠

liumaolin

b636027
07:53
Refactor SpeechMonitor to use active audio frame duration instead of count⁠

liumaolin

15891ec
07:53
Add TTS generation error handling and `is_task_interrupted` helper function⁠

liumaolin

5ecb408
07:52
Optimize VAD logic by replacing `np.max(probs)` with `any(prob >= threshold)` for improved readability and efficiency.

liumaolin

9273b76

Jul 3, 2025

04:12
Increase audio capture chunk size to 1024 in `capture.py` for smoother streaming

liumaolin

095cfb6
02:54
Remove `speech_monitor` dependency from `asr_worker` service definition.

liumaolin

5cf0dbe
02:31
Add echo cancellation and VAD toggle support in service factories and routes⁠

liumaolin

2ecfa8f

Jul 2, 2025

09:33
Fix help text for `--disable-echo-cancellation` to clarify the default behavior is not disabled

liumaolin

d846f85
09:30
Refactor threading in `launcher.py` to standardize worker initialization, enforce daemon mode, and improve naming consistency.

liumaolin

7d8046a
09:24
Handle overflow errors in audio capture by adding `exception_on_overflow=False` and skip processing when no data is available.

liumaolin

5f9eaee
09:23
Add `--disable-echo-cancellation` CLI option and update audio pipeline to support toggling echo cancellation and VAD

liumaolin

4e071d3
08:54
Integrate `SileroVAD` into `SpeechMonitor` for optional voice activity detection. Add `_detect_speech()` method and update queue handling logic. Implement `SileroVAD` as a singleton for efficient model management.

liumaolin

4e2e3d8
08:22
Increase queue timeout in audio and text processing services for smoother task handling

liumaolin

b446464
08:19
Refactor audio processing pipeline to normalize data in `SpeechMonitor` and streamline queuing in `AudioCapture`

liumaolin

57b0084
07:32
Update `AudioCapture` to support both PyAudio and macOS native AEC＋VAD libraries⁠

liumaolin

99e8988
06:54
Refactor to replace `EchoCancellingAudioCapture` with `AudioCapture` across the codebase for improved clarity and flexibility

liumaolin

7437d6d

Commit History

Jun 12

Bundle Qwen3-ASR weights in packaged app; slim PyInstaller assets⁠

Jun 11

ASR: use auto language detection to reject non-speech (fixes hallucination)⁠

Jun 10

Make Qwen3-ASR the default on main; bump to 1.2.0⁠

Add audio output device (speaker) selection⁠

Show the active ASR engine in the UI⁠

Fix websocket route registration for starlette >= 1.0⁠

ASR: add Qwen3-ASR engine, default zh/en to it on this branch⁠

Jun 9

Add external mic array support, UI i18n, glass settings redesign, and fixes⁠

Jul 24, 2025

refactor(core): Architecturally decouple Audio, ASR, and TTS modules⁠

Jul 23, 2025

简化LLM模型路径管理。

Jul 16, 2025

为LLMResponseGenerator类添加TaskStatusMixin混入，以增强任务有效性检查功能，确保在生成回答时任务状态的有效性。

Jul 15, 2025

更新音频任务处理逻辑，使用模型副本替代原始任务对象，以确保数据一致性和完整性。

重构处理LLM生成chunk内容的方法，以提高文本生成的准确性。

去除对 LLM 输出的处理

Jul 14, 2025

更新LLM模型参数，调整top_p值为0.8，并添加max_tokens参数，设置为32768。

更新用户配置文件，修复logger导入路径以确保正确加载日志记录功能。

Jul 11, 2025

添加获取TTS模型参考音频的API路由，支持通过模型ID获取音频文件。

Jul 10, 2025

更新API文档

缓存user_prompts以提高性能

调整prompt的逻辑，确保展示的提示词中不包含/no_think指令

添加设置相关的API路由⁠

调整LLM prompt的存放位置

增强任务有效性检查，添加日志记录以便于调试。

在生成TTS音频时始终记录生成信息。

在`SpeechStateMonitor`类的初始化过程中调用该方法，确保在创建新语音任务时中断任务ID被正确重置。

Jul 9, 2025

修复`PerformanceLogMixin`中的音频记录逻辑⁠

修复`PerformanceLogMixin`中的调试模式检查逻辑⁠

增强性能日志记录功能，新增用户问题日志记录方法⁠

Revise `ACTIVE_FRAME_THRESHOLD` from 0.32s to 0.1s

Jul 7, 2025

更新MoYoYo语音模型配置，修改文本分割方法并新增角色模型⁠

更新MoYoYo语音模型配置，新增优先级字段⁠

新增Mixin类以增强语音任务处理功能⁠

添加MoYoYo语音模型“白岩松”及相关文件⁠

Jul 6, 2025

重构`is_task_interrupted`方法以检查语音任务中断状态⁠

Jul 4, 2025

Add `has_no_words` check to skip punctuation-only TTS tasks and enhance debug logs⁠

Refactor SpeechMonitor to use active audio frame duration instead of count⁠

Add TTS generation error handling and `is_task_interrupted` helper function⁠

Optimize VAD logic by replacing `np.max(probs)` with `any(prob >= threshold)` for improved readability and efficiency.

Jul 3, 2025

Increase audio capture chunk size to 1024 in `capture.py` for smoother streaming

Remove `speech_monitor` dependency from `asr_worker` service definition.

Add echo cancellation and VAD toggle support in service factories and routes⁠

Jul 2, 2025

Fix help text for `--disable-echo-cancellation` to clarify the default behavior is not disabled

Refactor threading in `launcher.py` to standardize worker initialization, enforce daemon mode, and improve naming consistency.

Handle overflow errors in audio capture by adding `exception_on_overflow=False` and skip processing when no data is available.

Add `--disable-echo-cancellation` CLI option and update audio pipeline to support toggling echo cancellation and VAD

Integrate `SileroVAD` into `SpeechMonitor` for optional voice activity detection. Add `_detect_speech()` method and update queue handling logic. Implement `SileroVAD` as a singleton for efficient model management.

Increase queue timeout in audio and text processing services for smoother task handling

Refactor audio processing pipeline to normalize data in `SpeechMonitor` and streamline queuing in `AudioCapture`

Update `AudioCapture` to support both PyAudio and macOS native AEC＋VAD libraries⁠

Refactor to replace `EchoCancellingAudioCapture` with `AudioCapture` across the codebase for improved clarity and flexibility