Speech Recognition AI Models in 2026, Capabilities & Comparisons | AIPortalX

Filters

Selected Filters

Speech Recognition

Task1

Organization

Country

Include Other Tiers

Active Research

Legacy Models

By default, only production models are shown

30 Models found

Gemini Robotics-ER 1.5

By Google DeepMind

Domain

Task

Instruction interpretation

Robotic manipulation

Image captioning+5 more

Qwen3-Omni-30B-A3B

Domain

Vision+1 more

Task

Language modeling

Language generation

Question answering+6 more

gpt-realtime

Domain

Task

Speech recognition ASR

Speech synthesis

Visual question answering+1 more

Canary 1B v2

Domain

Task

Speech recognition ASR

Parakeet-tdt-0.6b-v3

Domain

Task

Speech recognition ASR

Gemini 2.5 Deep Think

Domain

Vision+2 more

Task

Language modeling

Language generation

Mathematical reasoning+6 more

Gemini 2.5 Flash-Lite Jun 2024

By Google DeepMind

Domain

Video+1 more

Task

Language modeling

Language generation

Question answering+9 more

Gemma 3n

Domain

Task

Language modeling

Language generation

Question answering+7 more

Gemini 2.5 Flash

By Google DeepMind

Domain

Vision+1 more

Task

Language modeling

Language generation

Question answering+9 more

Gemini 2.5 Pro

By Google DeepMind

Domain

Video+1 more

Task

Language modeling

Language generation

Question answering+6 more

Chirp 3 Speech-to-Text

Domain

Task

Speech recognition ASR

Reka Flash 3

Domain

Vision+1 more

Task

Code generation

Language modeling+6 more

Baichuan-Omni-1.5

Domain

Speech+2 more

Task

Language modeling

Language generation

Question answering+8 more

Gemini 2.0 Flash

By Google DeepMind

Domain

Audio+2 more

Task

Language modeling

Language generation

Question answering+9 more

Gemini 2.0 Pro

By Google DeepMind

Domain

Vision+1 more

Task

Code generation

Language modeling

Language generation+3 more