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

Llama new
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 13, 2025

03:44
Update static file routing and root endpoint for frontend integration⁠

liumaolin

f7b034a

Jun 12, 2025

08:17
Add robust lifecycle management for `audio_player` service in system routes⁠

liumaolin

627c3e7
07:47
Standardize service lifecycle management by replacing `stop` with `exit` and introducing `is_exited` check⁠

liumaolin

f5226c0
07:42
Remove `voice_schemas.py` and refactor schema imports for TTS and ASR modules in `__init__.py`

liumaolin

4895dc2
07:29
Refactor speech recognizer, audio capture, and system routes for improved clarity and functionality⁠

liumaolin

037e5ae
03:44
Add pause and resume functionality to voice dialogue system⁠

liumaolin

d701b8a
01:41
Refactor project: split `main.py` functionality into modular components under `cli`, `core`, and `config`.

liumaolin

d08a15b
01:38
Increase service startup timeouts and set daemon mode for services.

liumaolin

61524a8

Jun 11, 2025

07:33
Refactor imports in `whisper.py` and `funasr.py` to use absolute paths for `ensure_minimum_audio_duration`.

liumaolin

d673573
02:55
Update `moyoyo.py`: add fallback for `utils` to ensure `HParams` availability in runtime.

liumaolin

bd3673b
02:11
Refactor imports for consistency in `kokoro.py` and `processor.py`. Use absolute paths for better readability and maintainability.

liumaolin

8630353
02:09
Update `paths.py`: improve PROJECT_ROOT resolution with `_MEIPASS` support and enhance third-party path handling.

liumaolin

664d767

Jun 10, 2025

08:57
Rename 'src/VoiceDialogue' to 'src/voice_dialogue'.

liumaolin

511ff0c

Jun 9, 2025

10:31
Revamp API core description: expand feature details for ASR, LLMs, TTS, system control, and real-time communication; improve clarity and structure of documentation.

liumaolin

c57de2a
10:03
Update project requirements.

liumaolin

ccdd95f
10:00
Integrate WebSocket support: add `/api/v1/ws` endpoint, enable real-time message handling via `websocket_message_queue`, and refactor services and models to support WebSocket-based question and answer updates.

liumaolin

2534744
07:28
Refactor `SessionIdManager` module: rename `session_id_manager.py` to `session_manager.py` and update imports accordingly.

liumaolin

83ef092
07:27
Refactor session ID handling: replace `current_session_id` with `SessionIdManager` for thread-safe management, update related imports and references.

liumaolin

92bb56d
07:05
Refactor `__init__.py` in TTS runtime: streamline `__all__` handling, improve logging for import failures, and enhance maintainability of module exports.

liumaolin

6f036c6
07:05
Serve static frontend assets through FastAPI: mount static files and replace root endpoint response with `index.html`.

liumaolin

ad7bf8d
03:01
Handle `UnboundLocalError` in punctuation model lookup: add exception handling to ensure stability during transcription.

liumaolin

933e84c

Jun 6, 2025

10:12
Remove `VoiceDialogue` API, models, and settings: clean up unused modules and dependencies for the decommissioned service.

liumaolin

3eb6daa
09:59
Refactor assets files

liumaolin

1d3b1b4
09:34
Refactor directories across services: rename `audio_generator` to `generators`, `asr` to `recognizers`, and update all import paths for consistency and improved module organization.

liumaolin

919ff3f
09:28
Refactor imports across services: replace `services.core` module references with `core` for consistency and maintainability; remove unused `Queue` imports.

liumaolin

619c761
09:14
Refactor imports in TTS and ASR modules: switch to absolute imports for improved clarity and maintainability.

liumaolin

d7d0d96
07:40
Remove trailing whitespace in `audio_generator/manager.py` and `asr/manager.py` for improved code cleanliness and consistency.

liumaolin

f08ef5f
04:21
Refactor ASR manager: remove `_get_asr_supported_languages`, replace static language mapping with `supported_langs` attribute, and update dynamic module import to use `importlib.util` for improved maintainability.

liumaolin

8acaad0
03:46
Refactor `audio_generator/manager.py`: streamline imports, remove redundant modules in `register_all_tts`, and adjust dynamic import spec for improved maintainability.

liumaolin

ee4663a

Jun 5, 2025

11:27
Adjust sorting priority in `audio_generator/models/base.py`: prioritize `language_bonus` over `priority` for config selection.

liumaolin

3b73d5e
10:39
Refactor TTS module loading in `audio_generator/manager.py`: replace `importlib.import_module` with `importlib.util` for improved dynamic import handling and error logging.

liumaolin

9bfcd24
09:46
Update TTS speaker configuration: replace static mapping with dynamic retrieval, add available speaker listing, and update CLI argument parsing for improved flexibility and maintainability.

liumaolin

cf355e6
09:45
Refactor sentence processing in `text_generator.py`: centralize sentence end mark sets, streamline `_should_end_sentence` logic, and eliminate redundant parameter passing for improved clarity and maintainability.

liumaolin

1ae18a4
08:47
Refactor imports in `main.py`: reorder modules for better readability and remove redundant `load_third_party` call.

liumaolin

8d91cc1
08:36
Add Kokoro TTS support: integrate new TTS model, configuration, and runtime components for enhanced multilingual voice synthesis.

liumaolin

1cbd55c
06:33
Refactor ASR routes: replace `fastapi_request.state` with `fastapi_request.app.state` for consistent application-level state management.

liumaolin

d231de5
06:32
Enhance TTS model handling: add dynamic status tracking, model downloading, and default system configuration initialization with API updates to manage active and default TTS models effectively.

liumaolin

fb6d02a
06:30
Comment out logging statements in `audio_player.py` to disable performance logs and streamline runtime output.

liumaolin

87a7384
02:54
Refactor ASR routes and services: implement instance creation tracking with background task support, enhance `get_supported_languages` with current ASR language, and clean up unused schemas and routes for simplified management.

liumaolin

757f3be

Jun 4, 2025

10:33
Remove `SystemConfig` and `SystemStartRequest` imports and clean up `__all__` in `schemas/__init__.py` for simplified schema management.

liumaolin

51a672c
10:29
Remove `SystemConfig` and `SystemStartRequest` models and clean up related API routes and background tasks for simplified system startup and management.

liumaolin

e7ebdb0
10:20
Enhance system management and audio capture services: implement `SystemStatusResponse` updates with detailed state tracking, add `audio_capture` service creation and lifecycle management, and refactor API `/system` routes for improved status and control handling.

liumaolin

94c7b78
10:00
Extend TTS registry functionality and integrate default system configurations: implement prioritization logic, language preference handling, and fallback mechanisms in `TTSConfigRegistry`; refactor service factory and lifespan management to support dynamic TTS selection and initialization.

liumaolin

a28f7e3
09:12
Introduce core module for API lifecycle management: add configuration, service factories, service manager, and lifespan handlers to streamline application startup, shutdown, and service orchestration.

liumaolin

a16e0e5
08:21
Add system utilities and initialize core modules: implement `get_system_language` and `get_system_info`, update API startup with system defaults, and integrate ASR, LLM, and speech modules for enhanced functionality.

liumaolin

5c0e715
06:19
Refactor core queue initialization: move queue definitions to `constants.py` and clean up redundant imports in `main.py` for better modularity.

liumaolin

bfefeb3
03:47
Introduce initial API structure for VoiceDialogue: add dependencies, middleware, and routes for ASR, TTS, system, and voice modules.

liumaolin

8f823b0

Jun 3, 2025

09:47
Refactor ASR module: introduce modular structure with ASR interface, implement FunASR and Whisper clients, add registry, and consolidate utility functions for enhanced maintainability and extensibility.

liumaolin

59603db
08:26
Refactor TTS module: rename `tts_manager` to `manager` for consistency across imports and structure.

liumaolin

89f7f05
08:06
Refactor speech processing: add type hint for `_process_active_voice_frame` and replace `max()` with `np.max()` for consistency.

liumaolin

5284873

Commit History

Jun 13, 2025

Update static file routing and root endpoint for frontend integration⁠

Jun 12, 2025

Add robust lifecycle management for `audio_player` service in system routes⁠

Standardize service lifecycle management by replacing `stop` with `exit` and introducing `is_exited` check⁠

Remove `voice_schemas.py` and refactor schema imports for TTS and ASR modules in `__init__.py`

Refactor speech recognizer, audio capture, and system routes for improved clarity and functionality⁠

Add pause and resume functionality to voice dialogue system⁠

Refactor project: split `main.py` functionality into modular components under `cli`, `core`, and `config`.

Increase service startup timeouts and set daemon mode for services.

Jun 11, 2025

Refactor imports in `whisper.py` and `funasr.py` to use absolute paths for `ensure_minimum_audio_duration`.

Update `moyoyo.py`: add fallback for `utils` to ensure `HParams` availability in runtime.

Refactor imports for consistency in `kokoro.py` and `processor.py`. Use absolute paths for better readability and maintainability.

Update `paths.py`: improve PROJECT_ROOT resolution with `_MEIPASS` support and enhance third-party path handling.

Jun 10, 2025

Rename 'src/VoiceDialogue' to 'src/voice_dialogue'.

Jun 9, 2025

Revamp API core description: expand feature details for ASR, LLMs, TTS, system control, and real-time communication; improve clarity and structure of documentation.

Update project requirements.

Integrate WebSocket support: add `/api/v1/ws` endpoint, enable real-time message handling via `websocket_message_queue`, and refactor services and models to support WebSocket-based question and answer updates.

Refactor `SessionIdManager` module: rename `session_id_manager.py` to `session_manager.py` and update imports accordingly.

Refactor session ID handling: replace `current_session_id` with `SessionIdManager` for thread-safe management, update related imports and references.

Refactor `__init__.py` in TTS runtime: streamline `__all__` handling, improve logging for import failures, and enhance maintainability of module exports.

Serve static frontend assets through FastAPI: mount static files and replace root endpoint response with `index.html`.

Handle `UnboundLocalError` in punctuation model lookup: add exception handling to ensure stability during transcription.

Jun 6, 2025

Remove `VoiceDialogue` API, models, and settings: clean up unused modules and dependencies for the decommissioned service.

Refactor assets files

Refactor directories across services: rename `audio_generator` to `generators`, `asr` to `recognizers`, and update all import paths for consistency and improved module organization.

Refactor imports across services: replace `services.core` module references with `core` for consistency and maintainability; remove unused `Queue` imports.

Refactor imports in TTS and ASR modules: switch to absolute imports for improved clarity and maintainability.

Remove trailing whitespace in `audio_generator/manager.py` and `asr/manager.py` for improved code cleanliness and consistency.

Refactor ASR manager: remove `_get_asr_supported_languages`, replace static language mapping with `supported_langs` attribute, and update dynamic module import to use `importlib.util` for improved maintainability.

Refactor `audio_generator/manager.py`: streamline imports, remove redundant modules in `register_all_tts`, and adjust dynamic import spec for improved maintainability.

Jun 5, 2025

Adjust sorting priority in `audio_generator/models/base.py`: prioritize `language_bonus` over `priority` for config selection.

Refactor TTS module loading in `audio_generator/manager.py`: replace `importlib.import_module` with `importlib.util` for improved dynamic import handling and error logging.

Update TTS speaker configuration: replace static mapping with dynamic retrieval, add available speaker listing, and update CLI argument parsing for improved flexibility and maintainability.

Refactor sentence processing in `text_generator.py`: centralize sentence end mark sets, streamline `_should_end_sentence` logic, and eliminate redundant parameter passing for improved clarity and maintainability.

Refactor imports in `main.py`: reorder modules for better readability and remove redundant `load_third_party` call.

Add Kokoro TTS support: integrate new TTS model, configuration, and runtime components for enhanced multilingual voice synthesis.

Refactor ASR routes: replace `fastapi_request.state` with `fastapi_request.app.state` for consistent application-level state management.

Enhance TTS model handling: add dynamic status tracking, model downloading, and default system configuration initialization with API updates to manage active and default TTS models effectively.

Comment out logging statements in `audio_player.py` to disable performance logs and streamline runtime output.

Refactor ASR routes and services: implement instance creation tracking with background task support, enhance `get_supported_languages` with current ASR language, and clean up unused schemas and routes for simplified management.

Jun 4, 2025

Remove `SystemConfig` and `SystemStartRequest` imports and clean up `__all__` in `schemas/__init__.py` for simplified schema management.

Remove `SystemConfig` and `SystemStartRequest` models and clean up related API routes and background tasks for simplified system startup and management.

Enhance system management and audio capture services: implement `SystemStatusResponse` updates with detailed state tracking, add `audio_capture` service creation and lifecycle management, and refactor API `/system` routes for improved status and control handling.

Extend TTS registry functionality and integrate default system configurations: implement prioritization logic, language preference handling, and fallback mechanisms in `TTSConfigRegistry`; refactor service factory and lifespan management to support dynamic TTS selection and initialization.

Introduce core module for API lifecycle management: add configuration, service factories, service manager, and lifespan handlers to streamline application startup, shutdown, and service orchestration.

Add system utilities and initialize core modules: implement `get_system_language` and `get_system_info`, update API startup with system defaults, and integrate ASR, LLM, and speech modules for enhanced functionality.

Refactor core queue initialization: move queue definitions to `constants.py` and clean up redundant imports in `main.py` for better modularity.

Introduce initial API structure for VoiceDialogue: add dependencies, middleware, and routes for ASR, TTS, system, and voice modules.

Jun 3, 2025

Refactor ASR module: introduce modular structure with ASR interface, implement FunASR and Whisper clients, add registry, and consolidate utility functions for enhanced maintainability and extensibility.

Refactor TTS module: rename `tts_manager` to `manager` for consistency across imports and structure.

Refactor speech processing: add type hint for `_process_active_voice_frame` and replace `max()` with `np.max()` for consistency.

Remove `voice_schemas.py` and refactor schema imports for TTS and ASR modules in `init.py`

Refactor `init.py` in TTS runtime: streamline `all` handling, improve logging for import failures, and enhance maintainability of module exports.

Remove `SystemConfig` and `SystemStartRequest` imports and clean up `all` in `schemas/init.py` for simplified schema management.