ModelSpeech & Audio AIv1.3.0

AudioCraft

by Meta AI · free · Last verified 2026-03-17

AudioCraft is an open-source generative audio framework from Meta AI. It integrates MusicGen for music, AudioGen for sound effects, and the EnCodec codec into a single platform. This unified, modular design allows for text-to-audio generation and has become a key reference for audio LLM research.

https://github.com/facebookresearch/audiocraft ↗

B—Above Average

Adoption: BQuality: AFreshness: BCitations: AEngagement: F

Specifications

License: MIT
Pricing: free
Capabilities: Text-to-music generation, Text-to-sound effect generation, High-fidelity neural audio compression (EnCodec), Fine-tuning models on custom audio datasets, Modular architecture for combining and extending models, Command-line interface (CLI) for generation, Python API for programmatic access and integration, Support for pre-trained models for immediate use
Integrations: [object Object], [object Object], [object Object]
Use Cases: [object Object], [object Object], [object Object], [object Object], [object Object]
API Available: Yes
Parameters: 1.5B (MusicGen Large)
Context Window: N/A
Modalities: text, audio
Training Cutoff: 2023
Tags: audio-generation, music-generation, sound-effects, text-to-audio, open-source, meta-ai, generative-ai, deep-learning, python-framework, audio-codec, llm
Added: 2026-03-17
Completeness: 0.95%

Index Score

62.6

Adoption

Quality

Freshness

Citations

Engagement

Need help choosing the right model?

Get Expert Guidance

Explore the full AI ecosystem on Agents as a Service