VoxCPM2 is OpenBMB's Apache-2.0 tokenizer-free 2B text-to-speech model for 30 languages, voice design, controllable cloning, streaming, fine-tuning, and 48kHz output. This guide covers modes, deployment, evaluation, consent, provenance, and alternatives.
ChatTTS is a text-to-speech model designed specifically for dialogue scenario such as LLM assistant. It supports both English and Chinese languages.
Tetos is an open-source Python and CLI wrapper that provides a unified interface for multiple text-to-speech providers. It is useful for developers who want to compare or switch between Edge TTS, OpenAI, Azure, Google, Volcengine, Baidu, Minimax, Xunfei, Fish Audio, and other engines without rewriting every integration.
EmotiVoice is a free open-source multi-voice, prompt-controlled TTS engine from NetEase Youdao. It supports English and Chinese speech synthesis, more than 2,000 voices, emotional prompt control, and local deployment for researchers, developers, creators, and voice application prototypes.
ElevenLabs is an AI voice platform for text-to-speech, voice cloning, dubbing, speech-to-text, voice agents, and generative audio APIs.
A deep learning toolkit for Text-to-Speech, battle-tested in research and production
Hailuo AI TTS, also tied to MiniMax Audio, is a text-to-speech and voice-generation product for multilingual AI voices, voice cloning, and audio content workflows.
The best and most realistic voice tools currently available
IndexTTS is Bilibili’s open-source industrial-grade controllable and efficient zero-shot text-to-speech system. It is best for speech researchers and developers who need controllable TTS experiments, not for casual users looking for a polished web voice app.