New projects people are discovering or following across Pinokio.
A multi-voice AI audiobook generator built on Qwen3-TTS — annotate scripts with an LLM, assign unique voices to each character, per-line style instructions for delivery, clone voices from reference audio, design new voices from text descriptions, train custom voices with LoRA fine-tuning, and export to MP3 or Audacity multi-track projects
Paste long text, clean it into readable sections, summarize each section, and ask questions in-browser with WebGPU. Choose between LFM2.5 230M, 350M, 1.2B-Instruct, and 1.2B-Thinking.
A multi-voice AI audiobook generator built on Qwen3-TTS — annotate scripts with an LLM, assign unique voices to each character, per-line style instructions for delivery, clone voices from reference audio, design new voices from text descriptions, train custom voices with LoRA fine-tuning, and export to MP3 or Audacity multi-track projects
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
This app lets you swap faces between two images. Upload a source image and a destination image, then specify which faces to swap by their position from the left.
OTP verification is widely used in 2FA, with tools like OTP bots and generators enabling automation. OTP bypass techniques target platforms like Telegram, Discord, PayPal, and banks, exploiting vulnerabilities in OTP-based security systems.
Chatbot local con llama.cpp — sin internet, sin telemetría, 100% privado
Customizing Realistic Human Photos via Stacked ID Embedding https://github.com/TencentARC/PhotoMaker
Local AI song generator with an editable score — YuE2 on your GPU: full songs with vocals, sheet music, covers, exact replay. Native Windows app, no Python, installer with auto-update.
Zero-shot multilingual TTS (600+ languages) with voice cloning and voice design — Gradio UI (app/app.py)
Application firewall and network monitor — privacy-first, all data stays local. / Pare-feu applicatif et moniteur réseau — vie privée d'abord, toutes les données restent locales.
Upload MP3 files, split into chunks, and transcribe to text using Whisper.
Private local AI meeting assistant: record conversations, transcribe speech, identify speakers, search meeting history, and create structured notes without uploading recordings by default.
