Make-An-Audio-2

Music Generation

bytedance/Make-An-Audio-2

20024PythonMIT

An AI model that turns a written description into audio, such as dog barks, rain, or short music clips.

🎼 Music Generation🏷️ Podcast Audio🗣️ Text-to-Speech

Make-An-Audio-2 preview — Preview card generated by GitHub from the repository. Star counts on the card may lag behind the figures above.

Tool Info

Type🐙 Open Source

Stars200

Forks24

LanguagePython

LicenseMIT

Unlock the full analysis — free

You're reading the public preview of Make-An-Audio-2. The AI-written pros & cons, use cases, setup guide and audience fit are free with an account — no credit card. Pro adds AI comparisons (50 per 30 days) and member daily & weekly reports.

Compare Make-An-Audio-2 with alternatives

See how it stacks up against other music generation tools.

More Tools

YuE

12.5K

Turn lyrics into full songs with vocals, and let you create covers or edit music with AI.

openvino-plugins-ai-audacity

2.1K

AI plugins for Audacity that add noise removal, vocal/instrument separation, speech-to-text, and text-to-music generation.

ThinkSound

1.4K

An open-source sound generation model from the Qwen team that creates matching sound effects from text descriptions or video footage.

NotaGen

1.2K

NotaGen uses large language model training methods to compose classical sheet music, turning a style prompt into editable ABC notation you can play or print.

MiniMax-Music3

939

Generate full songs up to 5 minutes long on your own computer from lyrics and a style description.