Store

Ultra-lightweight text-to-speech (15M-80M params) — CPU optimized, 8 voices, ONNX-powered

Liquid Audio - LFM2.5-Audio-1.5B: speech-to-speech, ASR, and TTS powered by Liquid AI.

Tokenizer-free TTS for context-aware speech, voice cloning, and voice design. 2B params, 48kHz, 30 languages (Gradio UI).

Standalone Text-to-Speech using Orpheus TTS with a Gradio UI

LFM2.5-VL-450M (Liquid AI): compact vision–language model for image understanding. Gradio UI with upload/URL, prompt, and generation sliders.

A live 3D intelligence console for planet Earth.

Control plane for the KH Studio family — generation queues, episode render workers, health, models, and machine-level scheduling.

Lightweight CPU text-to-speech with preset voices and optional Hugging Face-authenticated voice cloning.

A live 3D intelligence console for planet Earth.

🎙️ Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning. High-quality text-to-speech synthesis supporting zero-shot voice cloning and streaming inference with natural emotional expression.

YouTube to MP3, Cohere transcription, TranslateGemma translation, OmniVoice TTS. https://github.com/PierrunoYT/VidLingo-Pinokio

Advanced text-to-speech with voice cloning, multi-speaker support, and background music generation using Higgs Audio V2

Multi-voice text-to-speech for stories and audiobooks, with local and cloud TTS engines plus optional LLM text processing.

Apple Silicon TTS — curated MLX-first models for cloning, multilingual speech, narration, and expressive voices.

Zero-shot multilingual voice cloning with cross-lingual synthesis, disentangled emotion control, pronunciation guidance, and speaking-speed control.

⚡️ Efficient 6B parameter image generation model with sub-second inference. Generate high-quality, photorealistic images with only 8 inference steps. Features bilingual text rendering (Chinese & English) and Single-Stream Diffusion Transformer architecture.

Zero-shot voice cloning across 24 languages and 21 Chinese dialects, plus instruction-driven voice design and semantic and acoustic speech editing.

BreezeBlue Breeze TTS 2 — open-weight bilingual (EN/ZH) text-to-speech with voice clone, voice design, voice direction, and inline vocal events. Requires an NVIDIA GPU with 12GB+ VRAM.

Qwen3.8-27B on 16-32 GB Nvidia GPUs one-click install for Windows / Linux

DeepSeek Harness: Everything is a Plugin.