---
title: "Audio to Video with a Waveform and Captions | ToolSugar"
description: "Turn an MP3 or voice recording into an MP4 with a moving waveform, in landscape, vertical or square. Captions are optional and run on your device."
canonical: https://toolsugar.com/tools/audio-to-video
image: https://toolsugar.com/og.png
---

# Audio to Video

Most social platforms will not accept a bare audio file, so this tool wraps yours in an MP4 with an animated waveform. It runs in your browser in landscape, vertical or square. Captions are optional and are transcribed in your browser too, after a Whisper model download. Only runs with captions on count toward the 5 free AI runs per rolling 24 hours.

Runs on your device

## How it works

1. Drop in an audio file. A video file also works, and only its sound is used.
2. Choose landscape, vertical or square.
3. Leave captions off for a plain waveform, or turn them on to have the audio transcribed on your device. Captions use a speech model download and count as a free AI run.
4. Make the video and download the MP4.

## Key facts

- **Output**: MP4 with H.264 video and AAC audio
- **Sizes**: 1280 x 720, 720 x 1280, or 720 x 720
- **Inputs**: MP3, WAV, M4A, AAC, OGG, FLAC, or a video file
- **Privacy**: Everything stays on your device, captions included
- **Limit**: Counts toward 5 free AI runs per 24 hours only with captions on

## Common uses

- Share a podcast clip on a platform that only takes video.
- Post a song demo or voice note in a vertical feed.
- Add spoken captions to an interview snippet so that people can follow it muted.

## Questions

### Is my audio uploaded?

No. Captions are transcribed by a Whisper model that runs in your browser, so the audio never leaves your device. Without captions no model is used at all and the run is not counted.

### Can I use my own background picture?

Not on this tool. It draws a waveform on a dark background. Text to Video accepts a background picture if you need one.

### Does the waveform follow the sound?

Yes. It is drawn from your actual audio samples, frame by frame, so quiet parts look quiet and loud parts look loud.

[Read the Audio to Video guide](https://toolsugar.com/blog/how-to-turn-audio-into-a-video)

## Related tools

- [Text to Video](https://toolsugar.com/tools/text-to-video)
- [Text to Speech](https://toolsugar.com/tools/text-to-speech)
- [Image to Video](https://toolsugar.com/tools/image-to-video)
- [AI Reel Generator](https://toolsugar.com/tools/ai-reel-generator)