psyb0t/qwenspeak repository overview

pip install -U "huggingface_hub[cli]"

# Speech tokenizer (used by all models)
huggingface-cli download Qwen/Qwen3-TTS-Tokenizer-12Hz --local-dir ./Qwen3-TTS-Tokenizer-12Hz

# CustomVoice: 9 preset speakers + emotion control
huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice --local-dir ./Qwen3-TTS-12Hz-1.7B-CustomVoice
huggingface-cli download Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice --local-dir ./Qwen3-TTS-12Hz-0.6B-CustomVoice

# VoiceDesign: natural language voice descriptions
huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign --local-dir ./Qwen3-TTS-12Hz-1.7B-VoiceDesign

# Base: voice cloning from reference audio
huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-Base --local-dir ./Qwen3-TTS-12Hz-1.7B-Base
huggingface-cli download Qwen/Qwen3-TTS-12Hz-0.6B-Base --local-dir ./Qwen3-TTS-12Hz-0.6B-Base

/your/models/dir/
  Qwen3-TTS-Tokenizer-12Hz/
  Qwen3-TTS-12Hz-1.7B-CustomVoice/
  Qwen3-TTS-12Hz-0.6B-CustomVoice/
  Qwen3-TTS-12Hz-1.7B-VoiceDesign/
  Qwen3-TTS-12Hz-1.7B-Base/
  Qwen3-TTS-12Hz-0.6B-Base/

curl -fsSL https://raw.githubusercontent.com/psyb0t/docker-qwenspeak/main/install.sh | sudo bash

cat ~/.ssh/id_rsa.pub >> ~/.qwenspeak/authorized_keys
qwenspeak start -d -m /path/to/your/models

qwenspeak start -d                        # foreground or detached
qwenspeak start -d --port 2223             # custom port (default 2222)
qwenspeak start -d -m /mnt/hdd/models     # custom models directory
qwenspeak start -d --processing-unit cuda                # GPU mode (requires NVIDIA Container Toolkit)
qwenspeak start -d --processing-unit cuda --gpus 0       # use only GPU 0
qwenspeak start -d --processing-unit cuda --gpus 0,1     # use GPUs 0 and 1
qwenspeak start -d --memory 4g --swap 2g --cpus 4  # 4GB RAM, 2GB swap, 4 CPUs
qwenspeak stop                             # stop
qwenspeak upgrade                          # pull latest image, asks to stop/restart if running
qwenspeak uninstall                        # stop and remove everything
qwenspeak status                           # show status
qwenspeak logs                             # show logs

docker pull psyb0t/qwenspeak

cat ~/.ssh/id_rsa.pub > authorized_keys
mkdir -p work host_keys logs

docker run -d \
  --name qwenspeak \
  --restart unless-stopped \
  --memory 4g \
  -p 2222:22 \
  -e "LOCKBOX_UID=$(id -u)" \
  -e "LOCKBOX_GID=$(id -g)" \
  -e "TTS_LOG_RETENTION=7d" \
  -v $(pwd)/authorized_keys:/etc/lockbox/authorized_keys:ro \
  -v $(pwd)/host_keys:/etc/lockbox/host_keys \
  -v $(pwd)/work:/work \
  -v $(pwd)/logs:/var/log/tts \
  -v /path/to/your/models:/models:ro \
  psyb0t/qwenspeak

ssh -p 2222 tts@localhost "tts list-speakers"

docker run -d \
  --name qwenspeak \
  --restart unless-stopped \
  --gpus all \
  -p 2222:22 \
  -e "LOCKBOX_UID=$(id -u)" \
  -e "LOCKBOX_GID=$(id -g)" \
  -e "PROCESSING_UNIT=cuda" \
  -v $(pwd)/authorized_keys:/etc/lockbox/authorized_keys:ro \
  -v $(pwd)/host_keys:/etc/lockbox/host_keys \
  -v $(pwd)/work:/work \
  -v $(pwd)/logs:/var/log/tts \
  -v /path/to/your/models:/models:ro \
  psyb0t/qwenspeak

# Get the YAML template
ssh tts@host "tts print-yaml" > job.yaml

# Edit it
vim job.yaml

# Submit (returns immediately with job ID)
ssh tts@host "tts" < job.yaml
# {"id": "550e8400-...", "status": "queued", "total_steps": 3, "total_generations": 7}

# Check progress
ssh tts@host "tts get-job 550e8400"

# View job log
ssh tts@host "tts get-job-log 550e8400"

# Follow job log (like tail -f)
ssh tts@host "tts get-job-log 550e8400 -f"

# List all jobs
ssh tts@host "tts list-jobs"

# Cancel
ssh tts@host "tts cancel-job 550e8400"

# Download results when done
ssh tts@host "get hello.wav" > hello.wav

# Global settings
dtype: float32
models_dir: /models
flash_attn: auto           # auto-detects; set true/false to override

# Generation defaults
temperature: 0.9
top_k: 50
top_p: 1.0
repetition_penalty: 1.05
max_new_tokens: 2048
streaming: false
no_sample: false

steps:
  - mode: custom-voice
    model_size: 1.7b
    speaker: Ryan
    language: English
    generate:
      - text: "Hello world"
        output: hello.wav
      - text: "I cannot believe this!"
        speaker: Vivian
        instruct: "Speak angrily"
        output: angry.wav

  - mode: voice-design
    generate:
      - text: "Welcome to our store."
        instruct: "A warm, friendly young female voice with a cheerful tone"
        output: welcome.wav

  - mode: voice-clone
    model_size: 1.7b
    ref_audio: ref.wav
    ref_text: "Transcript of reference"
    generate:
      - text: "First line in cloned voice"
        output: clone1.wav
      - text: "Second line"
        output: clone2.wav

ssh tts@host "create-dir refs"
ssh tts@host "put refs/happy.wav" < me_happy.wav
ssh tts@host "put refs/angry.wav" < me_angry.wav

steps:
  - mode: voice-clone
    ref_audio: refs/happy.wav
    ref_text: "transcript of happy ref"
    generate:
      - text: "Great news everyone!"
        output: happy1.wav
      - text: "I'm so glad to hear that"
        output: happy2.wav

  - mode: voice-clone
    ref_audio: refs/angry.wav
    ref_text: "transcript of angry ref"
    generate:
      - text: "This is unacceptable"
        output: angry1.wav

# List all jobs
ssh tts@host "tts list-jobs"
ssh tts@host "tts list-jobs --json"

# Get job details
ssh tts@host "tts get-job <uuid-or-prefix>"

# View job log
ssh tts@host "tts get-job-log <uuid-or-prefix>"

# Follow job log (like tail -f)
ssh tts@host "tts get-job-log <uuid-or-prefix> -f"

# Cancel a running or queued job
ssh tts@host "tts cancel-job <uuid-or-prefix>"

# List available speakers
ssh tts@host "tts list-speakers"

# Tokenize round-trip (encode audio → speech tokens → decode back)
ssh tts@host "tts tokenize input.wav"

# View last 20 lines
ssh tts@host "tts log"

# View last 100 lines
ssh tts@host "tts log -n 100"

# Follow (like tail -f)
ssh tts@host "tts log -f"

# Follow with initial 50 lines
ssh tts@host "tts log -f -n 50"

Host tts
    HostName your-server
    Port 2222
    User tts

claude plugin marketplace add psyb0t/agents
claude plugin install qwenspeak@psyb0t

codex plugin marketplace add psyb0t/agents
codex plugin add qwenspeak@psyb0t

openclaw skills install @psyb0t/qwenspeak

make build
make test    # build + run integration tests