pip install voxcpm

import soundfile as sf
import numpy as np
from voxcpm import VoxCPM

model = VoxCPM.from_pretrained("openbmb/VoxCPM1.5")

# Non-streaming
wav = model.generate(
    text="VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech.",
    prompt_wav_path=None,      # optional: path to a prompt speech for voice cloning
    prompt_text=None,          # optional: reference text
    cfg_value=2.0,             # LM guidance on LocDiT, higher for better adherence to the prompt, but maybe worse
    inference_timesteps=10,   # LocDiT inference timesteps, higher for better result, lower for fast speed
    normalize=False,           # enable external TN tool, but will disable native raw text support
    denoise=False,             # enable external Denoise tool, but it may cause some distortion and restrict the sampling rate to 16kHz
    retry_badcase=True,        # enable retrying mode for some bad cases (unstoppable)
    retry_badcase_max_times=3,  # maximum retrying times
    retry_badcase_ratio_threshold=6.0, # maximum length restriction for bad case detection (simple but effective), it could be adjusted for slow pace speech
)

sf.write("output.wav", wav, model.tts_model.sample_rate)
print("saved: output.wav")

# Streaming
chunks = []
for chunk in model.generate_streaming(
    text = "Streaming text to speech is easy with VoxCPM!",
    # supports same args as above
):
    chunks.append(chunk)
wav = np.concatenate(chunks)

sf.write("output_streaming.wav", wav, model.tts_model.sample_rate)
print("saved: output_streaming.wav")

# 1) Direct synthesis (single text)
voxcpm --text "VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech." --output out.wav

# 2) Voice cloning (reference audio + transcript)
voxcpm --text "VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech." \
  --prompt-audio path/to/voice.wav \
  --prompt-text "reference transcript" \
  --output out.wav \
  # --denoise

# (Optinal) Voice cloning (reference audio + transcript file)
voxcpm --text "VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech." \
  --prompt-audio path/to/voice.wav \
  --prompt-file "/path/to/text-file" \
  --output out.wav \
  # --denoise

# 3) Batch processing (one text per line)
voxcpm --input examples/input.txt --output-dir outs
# (optional) Batch + cloning
voxcpm --input examples/input.txt --output-dir outs \
  --prompt-audio path/to/voice.wav \
  --prompt-text "reference transcript" \
  # --denoise

# 4) Inference parameters (quality/speed)
voxcpm --text "..." --output out.wav \
  --cfg-value 2.0 --inference-timesteps 10 --normalize

# 5) Model loading
# Prefer local path
voxcpm --text "..." --output out.wav --model-path /path/to/VoxCPM_model_dir
# Or from Hugging Face (auto download/cache)
voxcpm --text "..." --output out.wav \
  --hf-model-id openbmb/VoxCPM1.5 --cache-dir ~/.cache/huggingface --local-files-only

# 6) Denoiser control
voxcpm --text "..." --output out.wav \
  --no-denoiser --zipenhancer-path iic/speech_zipenhancer_ans_multiloss_16k_base

# 7) Help
voxcpm --help
python -m voxcpm.cli --help

# Full fine-tuning
python scripts/train_voxcpm_finetune.py \
    --config_path conf/voxcpm_v1.5/voxcpm_finetune_all.yaml

# LoRA fine-tuning
python scripts/train_voxcpm_finetune.py \
    --config_path conf/voxcpm_v1.5/voxcpm_finetune_lora.yaml