Audio modelsGoogle

Gemini Omni Audio: model and API overview

Gemini Omni Audio is part of Google's Gemini Omni family. This card is for an audio workflow. It can create or transform audio material. Consider it when the desired result is sound, speech, or music. Input: Audio, Images; output: Audio.

External model reference page. This page does not confirm availability in Neiron.

Capabilities

Gemini Omni Audio: For audio workflows, it can create or transform audio material.

Input: Audio, Images; output: Audio.

Purpose: Audio processing; developer: Google; region: United States.

Use cases

Choose it for an audio workflow: Gemini Omni Audio, when the desired result is sound, speech, or music.Compare Gemini Omni Audio with related Gemini Omni models if the task allows a different input or output format.Before starting, confirm the input format and expected result (an audio file).

Reviewed facts

Developer

Google

Purpose

Audio processing

Input

Audio, Images

Output

Audio

Geography

United States

Verified

2026-08-26

Benchmarks

No comparable benchmark is recorded in this card.

Sources

What to verify before use

Parameters, limits, licensing terms, and, where applicable, pricing for Gemini Omni Audio change over time. Check the official Google documentation before integrating.

Expected result: an audio file. For a different input or output, see neighboring Gemini Omni cards.

For comparison, use the same text or audio source; check intelligibility, voice or music consistency, and audible artifacts.

FAQ

What is Gemini Omni Audio?

What task is Gemini Omni Audio suited to?

Create or transform audio material. Choose it when the desired result is sound, speech, or music.

What does Gemini Omni Audio accept and return?

Reviewed input modalities: Audio, Images. Output: Audio. The record was checked on 2026-08-26.