Outstanding Tiny Desk AI Video Generator

How the Outstanding Tiny Desk AI video gets made

1. Open the video generator on this page with Soul Duet already selected, or choose another template. Soul Duet sets two singers at a shared microphone, with guitar, drums and keys behind them.
2. Upload clear photos into the labelled performer slots. Personal inspiration needs one photo for the left singer. Choose Group inspiration to replace either or both singers; other templates support up to five photos.
3. Choose 9:16 or 16:9 and generate. The tool creates a new scene, performance and original song. Processing time varies with demand. See the step-by-step guide for the full workflow.
4. Review the result and download the 15-second, 720p MP4 from your creations.

Which photos work for this scene

Use a front-facing or slightly turned face in even light. Keep the face sharp and large enough to see, without sunglasses, heavy filters or hands covering it. For Soul Duet, Personal inspiration replaces the left singer with one portrait. In Group inspiration, upload a portrait into either or both singer slots. If your source is a two-person photo, crop each person into their own image first.

Use photos of yourself or consenting adults. Do not upload celebrities or public figures. See the photo guide for examples and practical checks.

Outstanding Tiny Desk AI template: solo or group

A template is a scene preset, not code or a separate download. The 7 templates set the room, music style and performer arrangement. Soul Duet is the two-singer soul preset: a shared microphone with acoustic guitar, drums and keyboard behind it. It evokes an intimate desk concert without copying a specific performance.

Personal inspiration uses one photo to replace the main performer. Group inspiration uses one or more photos in any selected roles; unfilled optional roles are generated. Duo templates use the left singer in Personal inspiration and either or both singers in Group inspiration. The maximum number of photos depends on the template, with up to five supported. A single group photo does not automatically populate every slot.

15 seconds, and why the length matters

Each clip runs 15 seconds: enough time to establish the room and hear the vocal, while staying short enough for a social post. Choose 9:16 for a vertical feed or 16:9 for a wider view of the band. Every template supports both output formats at the same credit cost.

What you get and what it costs

The one-time packs are $9.99 for one video, $19.99 for three, and $29.99 for five. There is no subscription. Each generation uses one video credit and produces a 15-second, 720p MP4 with audio and no watermark.

Failed generations return their credits. Unused credits are eligible for a refund within 14 days under the refund policy. See pricing for the current packs before purchasing.

About the song

The music is generated for your clip from prompts requesting original music and lyrics. It is not the original Outstanding song or a licensed recording by any artist. The templates describe a band, a room and a lead vocal without requesting an existing song or an artist imitation. AI output varies, so listen to and review the result before sharing.

This is an independent AI video tool, not affiliated with or endorsed by NPR, Tiny Desk Concerts or any artist. Label your clip as AI-generated and use only images you have permission to use.