How to make an AI video from an audio track
How do I make an AI video that follows a voiceover, song or audio track?
Use a model that takes audio as an input. LTX 2.3 Audio to Video animates an image in time with a soundtrack. Seedance 2.0, Seedance 2.5 and MiniMax H3 take an audio clip as a reference alongside images and video. Make the voice or music first, with ElevenLabs or Stable Audio in the same workflow if you need it, and connect it to the video node.
Models that do this
| Model | Maker | Pick it for | Takes | Credits per run |
|---|---|---|---|---|
| LTX 2.3 (Audio to Video) | Lightricks | Animates one image to a soundtrack | Prompt plus audio or image | 92 (from €0.92) |
| Seedance 2.0 | ByteDance | Audio as a reference, up to 15 seconds | Prompt plus image, video or audio | 75 to 2,152 (from €0.75) |
| Seedance 2.5 | ByteDance | Audio as a reference, up to 30 seconds | Prompt plus image, video or audio | 76 to 6,379 (from €0.76) |
| MiniMax H3 | MiniMax | Images, video and audio references | Prompt plus image, video or audio | 85 to 359 (from €0.85) |
The lowest-cost option here is Seedance 2.0, from 75 credits (€0.75) per run. Credits are OTOY Studio's currency: 1 credit = €0.01. Prices are list prices before plan discounts (paid plans take 10% to 25% off every run). Every model is on every plan, including Free.
How to do it in OTOY Studio
- Add your audio: upload a file, or generate a voiceover with an ElevenLabs node or music with Stable Audio.
- Add the image the video should start from.
- Add an audio-capable video node and connect the audio and the image.
- Describe the performance or the visuals in the prompt and run it.
Related
Try it free: https://app.otoy.studio (the free plan includes 100 credits a month, no credit card).
Model prices are computed from OTOY Studio's billing configuration, exported 2026-10-20.