Vai al contenuto
AI.info

Model Tracker

Qwen-Audio

Qwen-Audio is an AI model made by Alibaba Tongyi. Alibaba Tongyi released it on 30 November 2023. It takes audio, text and returns text. Its weights are open.

In inglese

Alibaba Tongyi

Released
30 November 2023 — github.com, read 16 October 2026
Status
Not confirmed: The maker's pages reviewed do not state whether Qwen-Audio is preview, generally available, deprecated, or retired.
Takes
Audio, Text — github.com, read 16 October 2026
Returns
Text — github.com, read 16 October 2026
Open weights
Yes — github.com, read 16 October 2026
Licence
Not confirmed: two readings disagree: Tongyi Qianwen LICENSE AGREEMENT and Check our license at LICENSE
Context window
Not confirmed: The model card and maker documentation reviewed do not print a standard context-window size in tokens.
Longest answer
Not confirmed: The model card and maker documentation reviewed do not print a standard maximum output length in tokens.
Knowledge cutoff
Not confirmed: The maker's pages reviewed do not state a knowledge-cutoff date.
API price, input
Not confirmed: The maker's pages reviewed do not publish a standard API input price for Qwen-Audio.
API price, output
Not confirmed: The maker's pages reviewed do not publish a standard API output price for Qwen-Audio.
Where
Downloadable weights — github.com, read 16 October 2026
Parameters
8,000,000,000 — huggingface.co, read 16 October 2026
Model card
Not confirmed: two readings disagree: https://huggingface.co/Qwen/Qwen-Audio and https://github.com/QwenLM/Qwen-Audio/blob/main/README.md

Questions

When was Qwen-Audio released?

Alibaba Tongyi released Qwen-Audio on 30 November 2023.

Are the weights of Qwen-Audio open?

Yes: Alibaba Tongyi publishes the weights of Qwen-Audio for download.

What does Qwen-Audio take and return?

Qwen-Audio takes audio, text and returns text.

How many parameters does Qwen-Audio have?

Qwen-Audio has 8,000,000,000 parameters, as Alibaba Tongyi publishes it.

More from Alibaba Tongyi

Sources

  1. Qwen-Audio (read 16 October 2026)
  2. LICENSE (read 16 October 2026)
  3. Qwen-Audio (read 16 October 2026)

All of the Model Tracker