The wav2letter project provides an automatic speech recognition toolkit from Facebook AI Research.
AudioCraft
AudioCraft provides research code for generating music and sound effects and for audio compression.
About AudioCraft
AudioCraft is a research code base from Meta AI for generative audio. It includes MusicGen for text-to-music generation, AudioGen for text-to-sound generation from environmental sounds, and EnCodec for compression after training on raw audio signals.
The models use EnCodec to convert raw waveforms to discrete tokens, a single autoregressive language model to model the tokens, and the EnCodec decoder to produce the output waveform, with conditioning such as a pretrained text encoder for text-to-audio use.
Key features
- Generate music samples from user-provided text inputs
- Generate environmental sounds from text descriptions
- Compress raw audio into discrete token streams
- Convert generated tokens back to audio waveform
- Control generation with pretrained text-encoder conditioning
- Model parallel token streams with interleaving pattern
Best for: Researchers and developers working with generative models for music, sound effects, and audio compression.
Good for
- Combines music, sound effects, and compression in one code base
- Works from raw audio signals through discrete tokens
- Uses a single autoregressive model for token sequences
AudioCraft at a glance
- Website
- audiocraft.metademolab.com
- Category
- AI & Machine Learning › AI Voice & Audio
- Type
- Online tool
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
AudioCraft alternatives
Tools and sites you could use instead, ranked by how closely they match.
Google Illuminate turns research papers into AI-generated audio summaries to help users understand their content.
Pick
15 alternatives
AceTagGen provides a structured SUNO prompt builder, a prompt scoring tool, and research articles about music tags.
Text-to-Audio Generation with Latent Diffusion Models - Speech Research.
Sound Effect AI generates original sound effects for audio production instead of extracting effects from existing videos.
Paid
6 alternatives
OptimizerAI generates sound effects from text prompts for creators, game developers, and video makers.
Popular in AI Voice & Audio
Well-known listings from the same topic.
Alteredaltered.aiELSA Speakelsaspeak.comKreadoAIkreadoai.comPodwisepodwise.aiAddsubtitleaddsubtitle.aiAI Wedding Toastaiweddingtoast.com
AudioCraft FAQ
What is the difference between MusicGen and AudioGen?
MusicGen generates music samples from text inputs, while AudioGen generates environmental sounds from text.
How do AudioCraft models generate audio?
EnCodec converts raw audio to discrete tokens, a single autoregressive language model models the tokens, and the EnCodec decoder converts them back to a waveform.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.