VoxCPM
Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
GraphCanon updated 3w · GitHub synced 3w
Decision brief
VoxCPM is a tokenizer-free TTS tool excelling in multilingual speech generation, creative voice design, and lifelike cloning.
Good fit when
- When you need to generate high-quality, lifelike voice clones for multiple languages without the overhead of tokenizers.
- For applications requiring true-to-life voice design that benefits from tokenizer-free operation for smoother integration into multilingual projects.
Avoid when
- If your project is constrained by hardware with less powerful GPUs than NVIDIA RTX 4090, as VoxCPM might not provide optimal real-time factor performance.
- When a simple text-to-speech solution suffices and does not require the advanced features like voice cloning or creative voice design that VoxCPM offers.
- Requirements:
- Python >= 3.10 (<3.13), PyTorch >= 2.5.0, CUDA >= 12.0.; For production deployment, Nano-vLLM is recommended for its high throughput and concurrent request support.
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Active (20d since push)
- As of 3w
- Provenance
- Not a fork · Organization account
- As of 3w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install VoxCPMSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
VoxCPM2 is a text-to-speech tool capable of multilingual speech generation, voice cloning, and design, featuring tokenizer-free operation.
Capability facts
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Jul 29, 2026
- Languages
- python
Source: github.language+pyproject.toml · Jul 29, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Jul 29, 2026)
> **Requirements:** Python ≥ 3.10 (<3.13), PyTorch ≥ 2.5.0, CUDA ≥ 12.0. See [Quick Start Docs](https://voSource link
Tags
README
Installation
pip install voxcpm
Requirements: Python ≥ 3.10 (<3.13), PyTorch ≥ 2.5.0, CUDA ≥ 12.0. See Quick Start Docs for details.
🚢 Production Deployment (Nano-vLLM)
For high-throughput serving, use Nano-vLLM-VoxCPM — a dedicated inference engine built on Nano-vLLM with concurrent request support and an async API.
pip install nano-vllm-voxcpm
from nanovllm_voxcpm import VoxCPM
import numpy as np, soundfile as sf
server = VoxCPM.from_pretrained(model="/path/to/VoxCPM", devices=[0])
chunks = list(server.generate(target_text="Hello from VoxCPM!"))
sf.write("out.wav", np.concatenate(chunks), 48000)
server.stop()
RTF as low as ~0.13 on NVIDIA RTX 4090 (vs ~0.3 with the standard PyTorch implementation), with support for batched concurrent requests and a FastAPI HTTP server. See the Nano-vLLM-VoxCPM repo for deployment details.
Install from source (latest main — vllm-omni is rapidly evolving)
uv pip install vllm==0.19.0 --torch-backend=auto git clone https://github.com/vllm-project/vllm-omni.git && cd vllm-omni uv pip install -e .
See the [vLLM-Omni installation guide](https://vllm-omni.readthedocs.io/en/latest/getting_started/installation/) for other platforms (ROCm, XPU, MUSA, NPU) and Docker images.
```bash
---
## 📄 License
VoxCPM model weights and code are open-sourced under the [Apache-2.0](LICENSE) license.
For agents
This page has a .md twin and JSON over the API.