Qwen PC Edition Adds AI Voice Input for Direct Speech-to-Text in Apps
On May 7, Qwen introduced AI-powered voice input for PCs, enabling users to activate it via hotkeys in any desktop application. The feature can eliminate filler words, correct mistakes, and format spoken content, while also adapting its responses based on context. Users can also issue commands for writing, answering questions, or translating.
Qwen's voice input showcases strong semantic parsing. For instance, when given a spoken passage with speech errors like, "Boss Wang, the meeting is scheduled at two o'clock... no, three o'clock, the location is the old meeting room, remember to bring that... market research report," Qwen can filter out filler words like "um" or "that" in real time, correct the errors, and output structured text directly: "Boss Wang, the meeting is scheduled at 3 p.m., the location is the old meeting room, please bring the market research report."

Restructuring colloquial speech goes beyond simple text simplification; it also involves correcting logical errors and organizing content structurally. When users draft weekly reports or meeting minutes, even if their expressions are logically disjointed, Qwen can perform semantic summarization based on the context. For example, if a user casually mentions work progress, Qwen can automatically organize it into a structured weekly report with clear bullet points.
While working or creating, users can rely on Qwen via voice commands without leaving the editor. For instance, to insert last year's GDP data into the text, simply say, "Insert the national GDP data for 2025." When browsing websites or reading professional English papers, if something is unclear, select the text and say, "Explain this" or "Translate this," and Qwen will automatically provide explanations or translations.
In scenarios like DingTalk, WeChat, or emails, users can also ask Qwen to generate replies based on the context. For example, when replying to an English email from a client, users can simply state their requirements in Chinese verbally, and Qwen will generate a properly formatted English email reply in the input box.
Currently, Qwen's voice input feature is fully available, and all users can freely use it through the Qwen PC client.
Related article
Spotify aims to become the home for AI-generated personal audio
In recent years, tools such as Google’s NotebookLM, Hero, and Adobe Acrobat have empowered users to generate podcasts from source materials like documents, schedules, and articles. Spotify now enables access to these audio files within its platform,
AI LIVE London: Transforming AI and Industrial Automation
AI LIVE: The London Summit takes place 20–21 October 2026 at Olympia London. Credit: BizClikAI LIVE: The London Summit convenes global leaders to resolve operational bottlenecks and scale AI across industrial automation.The primary constraint on indu
Google’s Genie world model now simulates real streets with Street View
Most of us have used Google Street View to show a friend our old neighborhood or dropped the little person icon into Paris to check if our hotel is in a trendy area. Now, imagine experiencing that with full immersion and interactivity—simulating the
Related Special Topic Recommendations
Comments (1)
0/500
On May 7, Qwen introduced AI-powered voice input for PCs, enabling users to activate it via hotkeys in any desktop application. The feature can eliminate filler words, correct mistakes, and format spoken content, while also adapting its responses based on context. Users can also issue commands for writing, answering questions, or translating.
Qwen's voice input showcases strong semantic parsing. For instance, when given a spoken passage with speech errors like, "Boss Wang, the meeting is scheduled at two o'clock... no, three o'clock, the location is the old meeting room, remember to bring that... market research report," Qwen can filter out filler words like "um" or "that" in real time, correct the errors, and output structured text directly: "Boss Wang, the meeting is scheduled at 3 p.m., the location is the old meeting room, please bring the market research report."

Restructuring colloquial speech goes beyond simple text simplification; it also involves correcting logical errors and organizing content structurally. When users draft weekly reports or meeting minutes, even if their expressions are logically disjointed, Qwen can perform semantic summarization based on the context. For example, if a user casually mentions work progress, Qwen can automatically organize it into a structured weekly report with clear bullet points.
While working or creating, users can rely on Qwen via voice commands without leaving the editor. For instance, to insert last year's GDP data into the text, simply say, "Insert the national GDP data for 2025." When browsing websites or reading professional English papers, if something is unclear, select the text and say, "Explain this" or "Translate this," and Qwen will automatically provide explanations or translations.
In scenarios like DingTalk, WeChat, or emails, users can also ask Qwen to generate replies based on the context. For example, when replying to an English email from a client, users can simply state their requirements in Chinese verbally, and Qwen will generate a properly formatted English email reply in the input box.
Currently, Qwen's voice input feature is fully available, and all users can freely use it through the Qwen PC client.
Spotify aims to become the home for AI-generated personal audio
In recent years, tools such as Google’s NotebookLM, Hero, and Adobe Acrobat have empowered users to generate podcasts from source materials like documents, schedules, and articles. Spotify now enables access to these audio files within its platform,
AI LIVE London: Transforming AI and Industrial Automation
AI LIVE: The London Summit takes place 20–21 October 2026 at Olympia London. Credit: BizClikAI LIVE: The London Summit convenes global leaders to resolve operational bottlenecks and scale AI across industrial automation.The primary constraint on indu
Google’s Genie world model now simulates real streets with Street View
Most of us have used Google Street View to show a friend our old neighborhood or dropped the little person icon into Paris to check if our hotel is in a trendy area. Now, imagine experiencing that with full immersion and interactivity—simulating the





Home






