AI music videos
An AI music video puts visuals to a song instead of a voiceover. You pick a song, AITuber generates visuals that match the music, and lyrics can appear as synced captions. You can generate the song inside AITuber, upload your own audio file, or paste a Suno song URL. This is the easiest way to turn a Suno song into an MP4 video.
What do I need?
- A song. Generate one in the app, upload an audio file, or import from a Suno URL.
- Credits.
- A free account is enough to generate. To download, your account must have had a paid plan at least once.
How do I create an AI music video?
- Open music video page.
- Pick your music. You can generate a new song, upload a file, or paste a Suno song URL.
- Trim the song if you only want part of it.
- Click Next Step.
- Pick a Video Mode: AI Images, AI Video, Cover Image, or Avatar.
- Pick quality and captions. Lyrics show as captions when captions are on.
- Click Generate. The credit estimate shows before you confirm.
Can I use my own music? (Suno to MP4)
Yes. Three ways:
- Upload a file: MP3, WAV, M4A, AAC, or OGG. Maximum 50 MB and 10 minutes.
- Paste a Suno song URL: AITuber imports the track for you.
- Generate in AITuber: 30 credits per song. AI lyrics cost 5 credits.
Full walkthrough for Suno users: Turn a Suno song into a music video.
How much does an AI music video cost?
Every music video has a base cost of 50 credits. Then you pay for the song (only if you generate it) and the visuals.
Part | Cost |
|---|---|
Base (every music video) | 50 credits |
Song generation (optional) | 30 credits |
AI lyrics generation (optional) | 5 credits |
AI Images mode | 1 to 30 credits per image, by quality |
AI Video mode, Basic | 4 credits per second |
AI Video mode, Premium | 15 credits per second |
Cover Image mode | 0 extra (base cost only) |
Avatar mode | 14 credits per second (840 per minute) |
Using your own uploaded song costs nothing extra. What each video type costs.
What are the visual modes?
- AI Images: a slideshow of AI images with motion, one image every few seconds.
- AI Video: AI video clips for the whole song. The most dynamic and the most expensive.
- Cover Image: one still cover image for the whole video, with an optional waveform. The cheapest mode.
- Avatar: a talking-head character performs over the music.
Why do the lyrics captions not match the song exactly?
Caption timing comes from word-level analysis of the audio. Sung words are harder to detect than spoken words, so a caption can differ from your lyric sheet. See Why captions do not always match my lyrics.
What are the limits?
- Uploaded audio: 50 MB, 10 minutes maximum.
- You can trim any song to the part you want.
- If generation fails, your credits come back automatically.
Related
Updated on: 09/08/2026
Thank you!