Instructions to use openbmb/VoxCPM-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VoxCPM
How to use openbmb/VoxCPM-0.5B with VoxCPM:
import soundfile as sf from voxcpm import VoxCPM model = VoxCPM.from_pretrained("openbmb/VoxCPM-0.5B") 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=True, # enable external TN tool denoise=True, # enable external Denoise tool 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, 16000) print("saved: output.wav") - Notebooks
- Google Colab
- Kaggle
Incredible work, and just a few questions!
#6
by MRU4913 - opened
- Any plans to add more languages later, like Japanese, Korean, and so on?
- Will it be possible to deploy this model with VLLM in the future?
- Any plan for emotion control?!
Thank you for your feedback!
Yes, we plan to support more languages in the future release.
VLLM deployment is currently a bit challenging, as it doesn’t play very nicely with DiT yet.
Introducing controllability (emotion, etc.) is also one of our main focuses going forward—stay tuned!
a couple of follow-up comments.
- Is there any plan to add Bahasa Indonesia, it's spoken by 270millions people so it would be impactful.
- If there is any rest api that's compatible with OpenAI like - https://github.com/remsky/Kokoro-FastAPI
- How can I add voxCPM to mlx-audio or sherpa-onnx?