Suno Adds Lip-Sync Video Maker to Music App
A new tab lets users turn AI songs into 15-second clips, but it draws criticism for adding complexity to the audio generation process.
By Amit Chukwu ·

Suno users now have a new tool to convert their generated songs into visual media. The company launched a feature called Visuals on Wednesday, allowing creators to produce static images and short video clips. The system automatically synchronizes lip movements with the lyrics of the track. This expansion moves the platform beyond audio generation into video creation.
The new tab is available in Create mode on web browsers, iOS, and Android devices. On the web interface, users can also access the tool by clicking the three-dot menu on a specific song in their library. From there, they can select which part of the track to visualize. The system limits each clip to a maximum length of 15 seconds. Users must select a reference image to start the generation process.
Suno provides three methods for creating that reference image. Users can choose from original character presets provided by the platform, upload their own photo or artwork, or generate a new image using descriptive text prompts. The image engine allows for specific aspect ratio selections to optimize output for different platforms. For video creation, users can designate the reference image as the start or end frame of the clip. A toggle switch enables automatic lipsyncing of vocals.
The feature includes a dedicated editing timeline where users can assemble individual clips into longer videos. Text overlays can be added to display song lyrics. The technology behind Visuals is the H3 Move AI model, which is based on the H3 architecture developed by MiniMax. Suno states that the AI has been optimized for its specific user base and includes additional protections.
New text and visual filters are designed to prevent the generation of specific artists, public figures, and copyrighted works. The feature operates on a separate credit system distinct from song credits. Users will need Visuals credits to generate videos and images, meaning they may incur additional costs. This follows the introduction of a Speech feature in October that allowed for the generation of spoken words and voiceovers.
The launch has drawn mixed reactions from the user base. Some users argue that the company should focus on improving its core song generation capabilities instead of diversifying. In the YouTube video announcing the release, one user commented, "FIX AUDIO BEFORE ADDING CRAP NOBODY ASKED FOR." Other commenters expressed similar sentiments in the discussion section, reflecting ongoing concerns about the platform's direction amidst high-profile lawsuits regarding its music generator.
More Tech · National news · Report a business · Got a Story?






