Best Audio Gen
Updated Daily
WaveNet is a deep neural network architecture for generating raw audio waveforms, introduced by researchers at DeepMind in a paper published in September 2016. It uses a dilated causal convolutional network to model audio signals directly at the sample level, producing more natural-sounding speech t...
Suno v3 is an AI music generation model released by Suno AI in early 2024, capable of producing full songs with vocals, lyrics, and instrumentation from brief text prompts.
Meta's 2023 generative speech model notable for zero-shot in-context text-to-speech and audio editing without requiring task-specific fine-tuning.
Meta's 2023 text-to-music model, part of the AudioCraft framework, capable of generating high-quality music up to several minutes long from text descriptions.
Google's 2022 audio generation model that produces coherent long-form speech and piano music by treating audio as sequences of discrete tokens.
Google DeepMind's 2023 fast parallel audio generation model that synthesizes natural-sounding dialogue from AudioLM tokens orders of magnitude faster than real time.
