Audio AI: Generate and Edit Audio with Artificial Intelligence

Audio-SDS: NVIDIA's AI that generates realistic sound effects from text, video and images

NVIDIA Audio-SDS is the new system for generating realistic sound effects from text, images and video. Two stages, maximum coherence and limitless creative applications.

NotebookLM AI: How to Create Free Audio Podcasts in Italian in a Few Clicks

NotebookLM AI allows you to generate podcasts and audio content in Italian in a free and natural way. All it takes is a text to obtain a narrative voice ready for YouTube, courses or storytelling.

AudioX: The AI Model That Generates Any Sound From Any Input

AudioX is an advanced AI model that generates lifelike sound from any input: text, images, videos, or other audio. Learn how the new standard for cross-modal audio generation works.

Moonshot AI Introduces Kimi-Audio: A New Open-Source Benchmark for AI Audio

Kimi-Audio is Moonshot AI's new open-source benchmark for audio understanding, generation and interaction. A fundamental step towards increasingly natural and multimodal AI.

nari-labs/dia: The TTS model that generates ultra-realistic dialogues in a single pass

nari-labs/dia is the first TTS model capable of generating natural speech in a single inference, taking AI speech synthesis to a whole new level.

LiveCC: The First LLM Optimized to Train AI on Real-World Video Transcripts

LiveCC is the first framework to train LLM on real, noisy video transcripts, bringing AI closer to authentic communication. A revolution in conversational intelligence.