Audio-Flamingo-3-hf is an audio-language model developed by NVIDIA. It accepts both audio and text inputs and generates text responses. The model uses a custom chat template that supports audio tokens and is provided in Hugging Face format for local inference and research purposes.
Audio Flamingo 3 Hf sits in PulseGate's Other AI category. It focuses on understanding and reasoning over audio content in combination with text instructions. Audio Flamingo 3 Hf is an open-source project aimed at AI researchers and multimodal application developers. Audio Flamingo 3 Hf is open source under the Open Source license. Audio Flamingo 3 Hf is available on the web, the command line, and API.
NVIDIA builds and maintains Audio Flamingo 3 Hf, and it first shipped in 2025. Development happens publicly on GitHub with 1.2k stars. Among its 3 catalogued features are Audio Understanding, Multimodal Chat, and Instruction Following.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do