Pierre Bruno

Lightning-Fast, On-Device, Multilingual TTS — Gradio, ONNX, 44.1kHz

AI-Powered Text-to-Speech with Voice Cloning using Chatterbox TTS and Gradio interface. Includes Turbo, Multilingual (23+ languages), and Original models.

NVIDIA PiD — Pixel Diffusion Decoder for high-resolution latent decoding. Gradio UI for Z-Image + 4× PiD upscale, plus CLI demos for Flux.

Hy-MT2 multilingual translation — Gradio UI for 33-language translation with Hy-MT2-1.8B and Hy-MT2-7B.

3.8B foundational text-to-image model by Microsoft — Lens and Lens-Turbo variants

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

YouTube to MP3, Cohere transcription, TranslateGemma translation.

Torch-free TTS via Moss-TTS-GGUF (llama.cpp + ONNX). Voice cloning with quantized GGUF weights.

🎮 Classic Tetris game with modern web UI. Play the timeless puzzle game in your browser with smooth controls, score tracking, and beautiful graphics.

🦙 Create custom Ollama models with your own system prompts and parameters. Easy-to-use Gradio interface for building personalized AI models with temperature control and custom instructions.

A local implementation of the Kokoro Text-to-Speech model, featuring dynamic module loading, automatic dependency management, and a web interface.

A beautiful Gradio web interface for Photoroom's PRX-1024-t2i-beta text-to-image model.

Gradio web interface for Photoroom's PRX-1024-t2i-beta text-to-image model