Skip to content
TechIndexSubmit
Back to directory

Inflect v3

Models174New

A family of lightweight, local text-to-speech models, including Mini, Micro, and Atom, with Mini having 34.31M parameters. It offers vocal-event tags, reference voice-tuning, and 48 kHz enhancement, running on CPU and CUDA.

Similar tools

  • Kitten TTS 2 Mini, Nano, and Pico are a family of open-weight text-to-speech AI models offering various parameter sizes, multilingual support, and multiple voices for efficient CPU inference.

    Models
  • tiny-voca is a fully open, 4.5M-parameter English text-to-speech AI model with two voices, designed for efficient, real-time operation on CPUs and in browsers.

    Models
  • Zyphra's compact, open-source text-to-speech model offering natural speech and high-fidelity voice cloning with 100 million parameters. It runs in real-time on various devices and allows steering emotion, pace, and delivery.

    Models
  • Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

    Models
  • A compressed video and audio diffusion model, reduced from 31B to 14B parameters, optimized for efficiency with 6 steps and INT8 quantization. It offers a more performant solution for generative AI tasks.

    Models
  • A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It emphasizes reasoning before answering.

    Models