ModelSpeech & Audio AIvMusicGen Large

MusicGen

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

MusicGen is an open-source text-to-music model from Meta AI that generates high-quality instrumental music from text descriptions. It can also be conditioned on a melody reference, providing a strong, controllable baseline for both research and commercial applications, trained on 20K hours of licensed music.

https://audiocraft.metademolab.com/musicgen.html ↗

B—Above Average

Adoption: B+Quality: AFreshness: BCitations: AEngagement: F

Specifications

License: CC-BY-NC 4.0
Pricing: free
Capabilities: Text-to-music generation, Melody-conditioned music generation, High-quality instrumental track creation, Stereo audio output (32kHz), Fine-tuning on custom datasets, Controllable generation parameters, Open-weights for research and commercial use, Single-stage auto-regressive transformer architecture
Integrations
Use Cases: [object Object], [object Object], [object Object], [object Object], [object Object]
API Available: Yes
Parameters: 3.3B
Context Window: N/A
Modalities: text, audio
Training Cutoff: 2023
Tags: music-generation, text-to-music, open-source, meta-ai, instrumental, generative-ai, transformer-model, audio-generation, creative-ai, melody-conditioning
Added: 2026-03-17
Completeness: 0.9%

Index Score

64.5

Adoption

Quality

Freshness

Citations

Engagement

Need help choosing the right model?

Get Expert Guidance

Explore the full AI ecosystem on Agents as a Service