VidTune: Creating Video Soundtracks with Generative Music and Contextual Thumbnails
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911420339191808 |
|---|---|
| author | Huh, Mina Fraser, C. Ailie Li, Dingzeyu Dontcheva, Mira Wang, Bryan |
| author_facet | Huh, Mina Fraser, C. Ailie Li, Dingzeyu Dontcheva, Mira Wang, Bryan |
| contents | Music shapes the tone of videos, yet creators often struggle to find soundtracks that match their video's mood and narrative. Recent text-to-music models let creators generate music from text prompts, but our formative study (N=8) shows creators struggle to construct diverse prompts, quickly review and compare tracks, and understand their impact on the video. We present VidTune, a system that supports soundtrack creation by generating diverse music options from a creator's prompt and producing contextual thumbnails for rapid review. VidTune extracts representative video subjects to ground thumbnails in context, maps each track's valence and energy onto visual cues like color and brightness, and depicts prominent genres and instruments. Creators can refine tracks through natural language edits, which VidTune expands into new generations. In a controlled user study (N=12) and an exploratory case study (N=6), participants found VidTune helpful for efficiently reviewing and comparing music options and described the process as playful and enriching. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12180 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VidTune: Creating Video Soundtracks with Generative Music and Contextual Thumbnails Huh, Mina Fraser, C. Ailie Li, Dingzeyu Dontcheva, Mira Wang, Bryan Human-Computer Interaction Multimedia Sound Audio and Speech Processing Music shapes the tone of videos, yet creators often struggle to find soundtracks that match their video's mood and narrative. Recent text-to-music models let creators generate music from text prompts, but our formative study (N=8) shows creators struggle to construct diverse prompts, quickly review and compare tracks, and understand their impact on the video. We present VidTune, a system that supports soundtrack creation by generating diverse music options from a creator's prompt and producing contextual thumbnails for rapid review. VidTune extracts representative video subjects to ground thumbnails in context, maps each track's valence and energy onto visual cues like color and brightness, and depicts prominent genres and instruments. Creators can refine tracks through natural language edits, which VidTune expands into new generations. In a controlled user study (N=12) and an exploratory case study (N=6), participants found VidTune helpful for efficiently reviewing and comparing music options and described the process as playful and enriching. |
| title | VidTune: Creating Video Soundtracks with Generative Music and Contextual Thumbnails |
| topic | Human-Computer Interaction Multimedia Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2601.12180 |