Skip to content
TechIndexSubmit
Back to directory

Kitten TTS 2 Mini/Nano/Pico

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.

Similar tools

  • 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.

    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
  • A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, AudioGen, MusicGen, Tortoise, RVC, Vocos, Demucs, SeamlessM4T, and Bark!

    AI Apps
  • An open-source, multilingual Text-to-Speech (TTS) model with approximately 131M parameters, capable of both speaking and singing. It supports 14 voices across multiple languages and is designed for efficient local execution.

    Models
  • Open-source LLM inference benchmarks — TTFT, TPOT, Throughput, Latency & Cost-per-token for models like Llama, Qwen, Gemma, DeepSeek, Gpt-Oss etc. deployed on different dedicated GPUs.

    Models