Inflect-Micro-v2: complete voice in 9.36M parameters
Inflect-Micro-v2 is a new, highly efficient text-to-speech model that operates under 10 million parameters. It is designed for local, low-footprint inference on CPUs and edge devices.
Why it matters
Small-scale AI models are critical for privacy-focused, offline, and resource-constrained computing environments.
like 86 Text-to-Speech PyTorch English speech-synthesis local-tts cpu edge-ai small-model base-model vits 24khz License: apache-2.0 Model card Files Files and versions xet Community 1 Copy to bucket new Listen Evaluation 1. Human blind preference 2. Predicted naturalness versus footprint 3. Intelligibility on unseen text 4. CPU runtime 5. Complete weight footprint Choose the right Inflect Run locally Install Python Download through the Hub ONNX Runtime Release profile Package map Limitations Responsible use License, integrity, and attribution Private training scope and contact Citation
Complete local text-to-waveform speech synthesis under 10M parameters. Fixed-voice English TTS with deterministic seeds, long-text handling, and CPU or CUDA inference.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in