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

Detect speech presence and timestamps with accuracy and speed using the ultra-lightweight Silero VAD model

Analyzes an uploaded song and returns its duration and recognized lyrics with timing information when available.

Analyzes a song from an audio URL and returns a written description, identified instruments, genres, and descriptive tags.

Choose the Nth image from an image URL list for workflows.

Transcribes generated or uploaded music into a downloadable archive that can include MusicXML, PDF sheet music, and timestamped lyrics.

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.

Structured Instructions Generation endpoint for Fibo Edit, Bria's newest editing model.