Pierre Bruno

Fast Image Generation with Sana Diffusion Model

Pixel-space text-to-image generation (no VAE), monocular depth estimation and 4x image restoration/upscaling with Iris-3B by Speridlabs

All-in-one Gradio UI for the MOSS-TTS Family: voice cloning, dialogue generation, voice design from text, and sound effects.

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

Zero-shot multilingual TTS (600+ languages) with voice cloning and voice design — Gradio UI (app/app.py)

The open-source ElevenLabs alternative. Local voice cloning, video dubbing, and real-time dictation — 646 languages, no API keys.

🎵 YouTube to MP3 downloader with a simple Gradio UI and bundled FFmpeg. Paste a YouTube link to download MP3.

A web interface for the Moondream3 vision-language model featuring image captioning, visual question answering, object detection, and object pointing.

Advanced 3B parameter language model with Gradio web interface, GPU acceleration, and complete privacy

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

Instant, Ultra-Realistic Text-to-Speech

High-quality Text-to-Speech powered by VyvoTTS LFM2 model with easy-to-use web interface

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

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

🌍 TranslateGemma - Google's open-source multilingual translation AI. Translate text across 55+ languages and extract/translate text from images. Powered by Gemma 3 architecture.

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

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

Pixel-space PRX text-to-image pipeline (~7B params, Qwen3-VL text encoder, no VAE)

🎙️ 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.

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