Discover
Model Catalog
Find the right model for the job. Start with what you want to do, or browse by type, and compare what each model needs and what it costs before you open it.
What do you want to do?
1-4 of 4 models for “Ask about a picture or video”
A audio understanding model to analyze audio content and answer questions about what's happening in the audio based on user prompts.
Audio reasoning variant of NVIDIA's Nemotron 3 Nano Omni. 30B A3B hybrid Transformer-Mamba MoE - accepts audio plus a prompt and returns text.
EyeDra is a Speaker Verification tool that compares two audio recordings to determine if they were spoken by the same person. It uses voice biometrics and speaker recognition for identity verification, authentication, security, and fraud prevention.
Morphix is a deepfake detector that analyzes audio and returns a confidence score indicating the likelihood that it was generated by AI. It detects synthetic or manipulated audio that was not recorded by a real human.