ChatTTS vs VoxCPM
Open-source speech synthesis projects compared
ChatTTS and VoxCPM both generate speech from text for expressive audio applications. ChatTTS focuses on dialogue in Chinese and English, while VoxCPM emphasizes multilingual speech, voice design, and cloning.
ChatTTS: Generate Expressive Speech for Dialogue
ChatTTS is a generative text-to-speech model built for dialogue, including assistant-style speech. It supports Chinese and English, multiple speakers, and controls for prosody such as pauses and laughter.
VoxCPM: Generate and Clone Multilingual Speech
VoxCPM is a tokenizer-free text-to-speech system for multilingual speech generation, voice design, and voice cloning. Its VoxCPM2 release targets teams and developers who need expressive speech synthesis and can support a 2B-parameter model.
| ChatTTS | VoxCPM | |
|---|---|---|
| Language | Python | Python |
| License | AGPL-3.0 | Apache-2.0 |
| Stars | 39.9k | 38.3k |
| Forks | 4.3k | 4.3k |
| Last analyzed | Oct 3, 2026 | Oct 3, 2026 |
Key differences
- ChatTTS targets conversational audio such as assistant dialogue; VoxCPM covers multilingual speech generation, voice design, and voice cloning.
- ChatTTS supports Chinese and English, with English described as experimental; VoxCPM supports 30 languages without requiring language tags.
- ChatTTS offers controls for dialogue cues such as pauses and laughter; VoxCPM supports natural-language voice descriptions and reference-based cloning with optional style instructions.
- ChatTTS code is licensed under AGPL-3.0, while its model has a separate CC BY-NC 4.0 license; VoxCPM lists Apache-2.0 for its code and model weights.
- ChatTTS reports a minimum of 4 GB of GPU memory for a 30-second clip; VoxCPM2 lists about 8 GB of VRAM and requires CUDA 12.0 or newer.
Choose ChatTTS if you…
- need Chinese or English dialogue synthesis with multiple speaker options.
- want to experiment with pauses, laughter, or other conversational delivery cues.
- can work within the model's research-use license and reported GPU requirements.
Choose VoxCPM if you…
- need speech generation across 30 supported languages.
- want voice design from text descriptions or cloning from reference audio.
- can support VoxCPM2's documented software and GPU requirements and need fine-tuning or deployment options.
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.