Newly Released
Home > AI Models > Qwen3 Omni 30b A3b Captioner

Qwen3 Omni 30b A3b Captioner

Provider: Alibaba Updated: 2026-01-09

Qwen3 Omni 30b A3b Captioner is an speech recognition model from Alibaba, designed for speech recognition and transcription.

Speech Recognition Newly ReleasedEnglish

Pricing

Input 15.8 CNY / 1M tokens
Output 12.7 CNY / 1M tokens
Text to Image -
Image to Image -
Text to Video -
Image to Video -

Capabilities

Input Types Video
Output Types Text
Function Calling Not supported
Session Cache -
Fine-Tuning Not supported
Prefix Cache -
Structured Output Not supported
Image Understanding -
Text Generation Supported
Text to Image -
Image to Image -
Text to Video -
Image to Video -
Open Source Status -

Parameters

Last Updated 2026-01-09
Context Length 64K
Max Input Tokens 32K
Max Output Tokens 32K
Max Thought Tokens -
TPM 100K
RPM -
Parameter Count -
Modalities Text
Language Support English
Best For Speech recognition and transcription
Resolution -
Video Duration -
Frame Rate -

Benchmarks

These benchmark scores summarize how the model performs across different tasks and evaluation sets.

AIME

Measures performance on difficult competition-level mathematics problems.

64
Math Index

Captures broad mathematical problem-solving and reasoning performance.

64