Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music
Upload audio or paste a YouTube URL and ask about speech, environmental sounds, music, timestamps, speakers, or long-form events. Audio Flamingo Next gives detailed answers.
Authors: Sreyan Ghosh1,2, Arushi Goel1, Kaousheik Jayakumar2, Lasha Koroshinadze2, Nishit Anand2, Zhifeng Kong1, Siddharth Gururani1, Sang-gil Lee1, Jaehyeon Kim1, Aya Aljafari1, Chao-Han Huck Yang1, Sungwon Kim1, Ramani Duraiswami2, Dinesh Manocha2, Mohammad Shoeybi1, Bryan Catanzaro1, Ming-Yu Liu1, Wei Ping1
1NVIDIA, CA, USA | 2University of Maryland, College Park, USA
Correspondence: sreyang@umd.edu, arushig@nvidia.com
This Model Is Best For
- Standard audio QA and instruction following across speech, sound, and music
- Assistant-style long-audio understanding with direct answers and follow-up chat
- Speech tasks such as ASR, paralinguistic understanding, and multilingual AST / speech translation
- Broad music captioning and audio description when you want an answer rather than a dense caption
If you need the most detailed long-form captions or timestamp-heavy scene breakdowns, use Audio Flamingo Next Captioner.
If you need explicit step-by-step timestamp-grounded reasoning traces, use Audio Flamingo Next Think.
Audio Input
OR
| YouTube URL | Prompt |
|---|