Find tools › Open-source projects › Images, video & voice

VoxCPM

Open-source project · by OpenBMB

Turn typed text into realistic spoken audio or clone a voice using a short audio clip.

For developersPopular126,601 installs a month

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Generate spoken dialogue in 30 languages from text
  • Design unique synthetic voices using natural language descriptions
  • Clone personal voices from short reference audio files

How to start

  1. Install the library with pip install voxcpm.

  2. Ensure you have a supported Python environment with PyTorch and CUDA enabled.

  3. Load the model and generate audio using VoxCPM.from_pretrained('openbmb/VoxCPM2') in Python.

  4. Save the generated waveform to a WAV file using soundfile.

Good to know. Requires a dedicated graphics card with CUDA 12.0 or higher and Python 3.10 to 3.12 to run locally.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: Apache-2.0You are allowed to use it under these terms.
  • Last updated 2026-11-09

More detail

VoxCPM is an open-source text-to-speech system that generates natural multilingual audio, designs voices from text descriptions, and clones voices from sample audio.

Traditional text-to-speech models often sound robotic or struggle to match nuanced emotions across languages. Reach for VoxCPM when you need studio-quality 48kHz speech across 30 languages, text-prompted voice creation, or accurate voice cloning.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-10-23. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map