Instructions to use BleuCPU/pocket-voice with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use BleuCPU/pocket-voice 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 BleuCPU/pocket-voice:Q4_0
# Run inference directly in the terminal:
llama cli -hf BleuCPU/pocket-voice:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf BleuCPU/pocket-voice:Q4_0
# Run inference directly in the terminal:
llama cli -hf BleuCPU/pocket-voice:Q4_0

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 BleuCPU/pocket-voice:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf BleuCPU/pocket-voice:Q4_0

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 BleuCPU/pocket-voice:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BleuCPU/pocket-voice:Q4_0

Use Docker

docker model run hf.co/BleuCPU/pocket-voice:Q4_0

LM Studio
Jan
Ollama
How to use BleuCPU/pocket-voice with Ollama:
```
ollama run hf.co/BleuCPU/pocket-voice:Q4_0
```
Unsloth Desktop

How to use BleuCPU/pocket-voice with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BleuCPU/pocket-voice:Q4_0

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": "BleuCPU/pocket-voice:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use BleuCPU/pocket-voice with Docker Model Runner:
```
docker model run hf.co/BleuCPU/pocket-voice:Q4_0
```

Lemonade

How to use BleuCPU/pocket-voice with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BleuCPU/pocket-voice:Q4_0

Run and chat with the model

lemonade run user.pocket-voice-Q4_0

List all available models

lemonade list

Hermes Agent

How to use BleuCPU/pocket-voice with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BleuCPU/pocket-voice:Q4_0

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 BleuCPU/pocket-voice:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use BleuCPU/pocket-voice with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BleuCPU/pocket-voice:Q4_0

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 "BleuCPU/pocket-voice:Q4_0" \
  --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"

Pocket Voice — NeuTTS-Air mirror

Unmodified mirror of two files from Neuphonic's NeuTTS-Air, used by the Pocket iOS app for on-device text-to-speech.

All credit for these models goes to Neuphonic. These files are redistributed under the Apache License 2.0, the license they were published under. No changes have been made.

File	Source	SHA-256
`neutts-air-Q4_0.gguf`	neuphonic/neutts-air-q4-gguf (`neutts-air-Q4_0.gguf`)	`bf66dc21b7588fe720cbdfeac1595e7b7c780515f8d8f1ff9a29062e4ac9119e`
`neucodec-decoder.onnx`	neuphonic/neucodec-onnx-decoder (`model.onnx`, renamed)	`2a43d034d7537a9251c547eba77204c3c77de7f1fb918ed494b6b71ba400ecd1`

SHA-256 hashes match Neuphonic's originals byte-for-byte.

For the latest versions, documentation, and terms, see Neuphonic's official repositories and https://github.com/neuphonic/neutts.

License

Downloads last month: 18

GGUF

Model size

0.7B params

Architecture

qwen2

Hardware compatibility

4-bit