Instructions to use openbmb/VoxCPM2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VoxCPM
How to use openbmb/VoxCPM2 with VoxCPM:
import soundfile as sf from voxcpm import VoxCPM model = VoxCPM.from_pretrained("openbmb/VoxCPM2") 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
Speed issue in results.
Thanks a lot for releasing this, I was waiting for a new VOX for quite some time.
There is an issue however, I give it around 20-30 secs of reference audio with full transcription (ultimate mode) and no matter what I generate, speed is always 2 or 3 times faster than it should be with incredibly good quality. Is this is known issue? Kind regards.
I don't think anyone else has reported a similar problem before, because ultimate mode cloning usually maintains the same speed as the reference audio. Could it be due to the sampling rate of the saved audio?
Thanks a lot for releasing this, I was waiting for a new VOX for quite some time.
There is an issue however, I give it around 20-30 secs of reference audio with full transcription (ultimate mode) and no matter what I generate, speed is always 2 or 3 times faster than it should be with incredibly good quality. Is this is known issue? Kind regards.
Faced the same issue on a run. Changing the seed (to 0 in that case) helped with the pacing.