Hi everyone! At Earth Species Project, we have been working on building a user-friendly UI to interact with NatureLM-audio, the first large audio-language model tailored specifically for bioacoustics. You can now try the NatureLM-audio demo on Hugging Face Spaces. Upload a short animal sound, ask questions, and see what the model does. This is still in very early stages — so we need your help to figure out what’s working, what isn’t, and how people want to use it.

🔈 Try the Demo
📃 Read the Blog Post
💬 Share feedback on Discourse
🔒 Join the waitlist for more features

Your input will directly shape the next phase of development. Give it a spin and let us know what you find!