Baidu Text-to-Speech vs VoxCPM

Baidu Text-to-Speech converts text into speech for applications and devices, with Chinese, English, mixed Chinese-English, and more than 70 voice styles available through its online service. Users can change speech rate, pitch, volume, and supported emotional effects; Chinese polyphonic characters can be annotated with pronunciation. Streaming synthesis can play audio nearly as text is entered, and long-text synthesis handles up to 100,000 Chinese characters in one request. Baidu provides HTTP and WebSocket APIs, online and offline SDKs, and Android and iOS SDKs for phones and smart devices. Offline synthesis is intended for settings with weak or no network access, including mobile apps, readers, robots, and smart hardware. Listed uses include audiobook reading, news and order announcements, and smart hardware. Short-text API requests must stay under 1,024 GBK bytes, with 120 bytes or less recommended. Export formats are MP3, PCM, and WAV. The service offers a free trial; offline trial and license plans are listed, while prices for other listed plans are not provided.

VoxCPM is an open-source text-to-speech system whose VoxCPM2 model generates expressive multilingual speech. It supports 30 languages and lists nine Chinese dialects. Voice Design can create a voice from a natural-language description without reference audio, and voice cloning is supported. Output is 48kHz audio, reference audio is accepted at 16kHz, and WAV is listed as an export format. A streaming generation API is available; the repository reports a real-time factor as low as about 0.3 on an NVIDIA RTX 4090. Full and LoRA fine-tuning can adapt the model from 5–10 minutes of audio. Documented deployment includes Python and CLI use, a local web demo, production serving and on-device inference. vLLM-Omni exposes an OpenAI-compatible /v1/audio/speech endpoint, while Nano-vLLM supports concurrent requests. Apple Silicon MPS and C++ inference on CPU, Metal, CUDA or Vulkan are documented. Code and weights use Apache-2.0 and are free for commercial use. Python installation requires Python 3.10 or later but below 3.13, PyTorch 2.5.0 or later and CUDA 12.0 or later. Voice Design and cloning results can vary, and unsupported languages may require testing or fine-tuning. VoxCPM is headquartered in Beijing, China.