Qwen's new Deep Research update lets you turn its reports into webpages, podcasts in seconds

Chinese e-commerce giant Alibaba’s famed Qwen team of AI model researchers and engineers has introduced a major expansion to its Qwen Deep Research tool, which is available as an optional modality that the user can activate on the web-based Qwen Chat (a competitor to ChatGPT).

With the update, users can not only generate comprehensive research reports with well-organized citations, but also interactive web pages and podcasts with multiple speakers – all within 1-2 clicks.

This functionality is part of a own editiondistinct from many of Qwen’s previous open-source model offerings.

While the feature depends on the open source models Qwen3 coder, Qwen imageAnd Qwen3-TTS to strengthen its core capabilities, the end-to-end experience – including research execution, web deployment and audio generation – is hosted and managed by Qwen.

This means users benefit from a managed, integrated workflow without having to configure infrastructure. That said, developers with access to the open source models could theoretically replicate similar functionality on private or commercial systems.

The update was announced via the team official X account (@Alibaba_Qwen) today, October 21, 2025, stating:

“Qwen Deep Research just got a major upgrade. It now creates not only the report, but also a live web page and a podcast – powered by Qwen3-Coder, Qwen-Image and Qwen3-TTS. Your insights, now visual and audible.”

Research output in multiple formats

The core workflow starts with a user request within the Qwen Chat interface. From there, Qwen works together by asking clarifying questions to shape the scope of the investigation, pulling data from the Internet and official sources, and analyzing or fixing any inconsistencies it finds, even generating custom code if necessary.

A demo video posted by Qwen on X goes through this process on Qwen Chat using the American SaaS market as an example.

In it, Qwen pulls data from multiple industry sources, identifies discrepancies in market size estimates (for example, $206 billion versus $253 billion), and highlights ambiguities in the U.S. share of the global figures. The assistant comments on the differences in scope between sources and calculates a compound annual growth rate (CAGR) of 19.8% between 2020 and 2023, and provides contextual analysis to support the raw numbers.

Once the survey is complete, users can click the “eyeball” icon below the output result (see screenshot), which will bring up a PDF-style report in the right pane.

Then, when viewing the report in the right pane, the user can click the “Create” button in the upper right corner and choose from the following two options:

1. “Web Developer” which produces a live, professional web pageautomatically implemented and hosted by Qwenusing Qwen3-Coder for structure and Qwen-Image for visuals.

2. “Podcast“, which, as it says, produces an audio podcastalso featuring dynamic multi-speaker narratives generated by Qwen3-TTS hosted by Qwen for easy sharing and playback.

This allows users to quickly convert a single research project into multiple forms of content (written, visual and audible) with minimal additional input.

The website contains inline graphics generated by Qwen Image, making it suitable for use in public presentations, classrooms or publications.

The podcast feature allows users to choose between 17 different speaker names as host and 7 as co-presenter, although I couldn’t find a way to preview the voice output before selecting them. It seems designed for deep listening on the go.

There was no way to change the language output that I could see, so mine appeared in English, as did my reports and initial prompts, even though the Qwen LLMs are multimodal. The voices were a little more robotic than other AI tools I’ve used.

Here is an example of a web page I generated about the similarities between authoritarian regimes throughout history, another on UFO or UAP sightingsand below this section a podcast about UFO or UAP sightings.

Although the website is hosted via a public link, the podcast must be downloaded by the user and cannot be linked to publicly, as far as I could see in my brief usage so far.

Note that the podcast is very different from the actual report – not just a straight-through audio version of it, but a new format in which two presenters discuss and tease the topic, using the report as a starting point.

The web page versions of the report also include new images that are not included in the PDF report.

Comparisons with Google’s NotebookLM

While the new capabilities have been well received by many early adopters, comparisons to other research assistants have surfaced, particularly Google’s. NotebookLMwhich recently left beta.

AI commentator and newsletter writer Chubby (@kimmonismus) noted on X:

“I am very grateful that Qwen provides regular updates, which is great.

But the attempt to build a NotebookLM clone within Qwen-3-max doesn’t sound very promising compared to Google’s version.”

While NotebookLM is built around organizing and querying existing documents and web pages, Qwen Deep Research focuses more on generating new research content from scratchwhere resources from the open web are merged and presented in multiple modalities.

The comparison suggests that while the two tools overlap in the overall concept – AI-enabled research – they diverge in approach and target audience.

Availability

Qwen Deep Research is now live and available via the Qwen Chat app. The feature can be accessed with the following URL.

At the time of writing, no pricing details have been provided for Qwen3-Max or the specific Deep Research capabilities.

What’s next for Qwen Deep Research?

By combining research guidance, data analysis and multi-format content creation in a single tool, Qwen Deep Research aims to streamline the path from idea to publishable output.

The integration of code, imagery and voice makes it especially attractive to content creators, educators and independent analysts who want to scale their research into web or podcast-friendly forms without having to switch platforms.

Still, comparisons to more specialized offerings like NotebookLM raise questions about how Qwen’s overall approach compares to depth, precision, and sophistication. Whether the power of multi-format implementation outweighs these concerns may depend on the user’s priorities – and whether they prioritize one-click publishing over tight integration with existing notes and materials.

For the time being, Qwen indicates that research does not end with a document, but starts with one document.

Let me know if you’d like to condense this into something shorter or tailored for a particular audience – newsletter, press-style blog, internal team explainer, etc.

Source link