https://www.solosoft.dev/tags/voxcpm/Recent content in VoxCPM on SoloSoftHugoen-usFri, 01 May 2026 00:00:00 +0000https://www.solosoft.dev/post/voxcpm-tts-2026/Fri, 01 May 2026 00:00:00 +0000https://www.solosoft.dev/post/voxcpm-tts-2026/<p>VoxCPM2 is a tokenizer-free text-to-speech (TTS) model developed by <a href="https://www.openbmb.cn/">OpenBMB</a>, an open-source AI research community affiliated with Tsinghua University and the Beijing Academy of Artificial Intelligence (BAAI). With 2 billion parameters, VoxCPM2 represents a paradigm shift in speech synthesis by operating directly on continuous speech representations, eliminating the need for discrete audio tokenizers that typically degrade voice quality.</p> <p>The model supports over 30 languages with capabilities spanning zero-shot voice cloning, voice design (creating entirely new voices from text descriptions), and real-time streaming inference. VoxCPM2 has quickly become one of the most talked-about open-source TTS models of 2026, competing directly with commercial offerings like ElevenLabs and OpenAI&rsquo;s TTS while remaining freely available under the Apache 2.0 license.</p>