{"slug": "inflect-v2-3-9m-and-9-3m-parameter-open-weight-tts-models", "title": "Inflect-v2: 3.9M and 9.3M parameter open-weight TTS models", "summary": "Inflect-v2, two open-weight English TTS models at 3.9M and 9.3M parameters, generate speech multiple times faster than real-time on CPU while delivering quality competitive with larger systems like KittenTTS, Piper, and Supertonic-3. The models support CPU, CUDA, PyTorch, and ONNX under Apache 2.0.", "body_md": "Post\n\n34\n\nIntroducing Inflect-v2, two exceptionally small, open-weight English TTS models at just 3.9M and 9.3M parameters. Both generate speech multiple times faster than real-time on CPU. Despite their size, Inflect-v2 delivers quality that is competitive with much larger lightweight TTS systems, including KittenTTS, Piper, and Supertonic-3.\n\nCPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0.\n\nSee it for yourselves:\n\nTry the Demos:\n\nCPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0.\n\nSee it for yourselves:\n\n[owensong/Inflect-Micro-v2](https://huggingface.co/owensong/Inflect-Micro-v2)[owensong/Inflect-Nano-v2](https://huggingface.co/owensong/Inflect-Nano-v2)Try the Demos:", "url": "https://wpnews.pro/news/inflect-v2-3-9m-and-9-3m-parameter-open-weight-tts-models", "canonical_source": "https://huggingface.co/posts/Nymbo/780726828379501", "published_at": "2026-07-25 20:38:30+00:00", "updated_at": "2026-07-25 20:52:24.116982+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-products", "ai-tools"], "entities": ["Inflect-v2", "KittenTTS", "Piper", "Supertonic-3", "PyTorch", "ONNX", "Apache 2.0"], "alternates": {"html": "https://wpnews.pro/news/inflect-v2-3-9m-and-9-3m-parameter-open-weight-tts-models", "markdown": "https://wpnews.pro/news/inflect-v2-3-9m-and-9-3m-parameter-open-weight-tts-models.md", "text": "https://wpnews.pro/news/inflect-v2-3-9m-and-9-3m-parameter-open-weight-tts-models.txt", "jsonld": "https://wpnews.pro/news/inflect-v2-3-9m-and-9-3m-parameter-open-weight-tts-models.jsonld"}}