
Get encoding metadata from video and audio files using FFmpeg API.

Get EBU R128 loudness normalization from audio files using FFmpeg API.

Vision reasoning variant of NVIDIA's Nemotron 3 Nano Omni. 30B A3B hybrid Transformer-Mamba MoE - accepts an image plus a prompt and returns text.

Get waveform data from audio files using FFmpeg API.
✦ newAsk NVIDIA Nemotron 3.5 Super questions about an image: describe scenes, read text and charts, and reason over what it sees.

Structured Prompt Generation endpoint for Fibo, Bria's SOTA Open source model.

Convert plain text into Fibo-Lite's transparent JSON-structured prompts - Bria's unique controllability layer that no closed model offers. Built for agentic and enterprise workflows.
✦ newExplore interactive worlds in real time with movement and camera controls.
✦ newExplore interactive worlds in real time with movement and camera controls.
![Fibo Edit [Structured Instruction]](https://v3b.fal.media/files/b/0a8b2483/UZdf2yfDnuLfTMdQeTNzT_328d7729251342ac8fbc5c8721feb5c5.jpg)
Structured Instructions Generation endpoint for Fibo Edit, Bria's newest editing model.

Direct continuous, realtime video streams with live prompts while preserving characters, settings, and story continuity.
✦ newDirect a continuous world in real time with image references and text prompts.
✦ newReal-time games rendered using VAST's Eden Live 14B
✦ newReal-time games rendered using VAST's Eden Live 5B