Gemini Ultra Voice

NEW HOT

Google · Gemini

API

Gemini Ultra Voice provides advanced multimodal understanding by seamlessly integrating voice, vision, and contextual reasoning for dynamic interactions.

TextVisionAudioReasoning

Scores 97% on MMLU, competitive across 4 standard benchmarks.

Data aggregated and editorially reviewed by TrendMing.

Benchmark Performance

MMLU97%

HumanEval89%

MATH87%

GPQA94%

Scores sourced from published evaluations. Higher = better.

Quick Specs

Context Window1M tokens

Parameters4T

Input pricing$0.004 / 1K audio-tokens

Output pricing$0.012 / 1K audio-tokens

Released2026-09-28

Back to AI Models