Convert an MP3 to an MP4 video with an image. Add your audio, add a cover image (or let Solmi draw a gradient with the track title), and it renders a 1280×720 video with an animated equalizer that you can upload straight to YouTube, TikTok, or Instagram. It runs entirely in your browser, so nothing is uploaded; it encodes in real time, about the length of the song; and it exports MP4 where your browser can record it (Safari, recent Chrome and Edge) and WebM elsewhere (e.g. Firefox). YouTube takes either file; for TikTok or Instagram, post the MP4. Supports MP3, WAV, M4A, AAC, OGG, and FLAC.
Step one: choose the audio file. MP3 is the usual input, but WAV, M4A, AAC, OGG, and FLAC all work because the browser decodes them the same way. Step two: add an image, or don't. With an image, the picture becomes the background of the video; without one, Solmi draws a gradient and prints the track's title. Step three: press Create video and wait about the length of the song while the browser records the frames and the audio together, then download the result. There is no account, no queue, and no upload; the whole conversion happens on your device.
The image is scaled to cover the full 1280×720 frame and centered, so a square album cover is cropped top and bottom to fit 16:9 and a landscape photo fits as is. A soft dark gradient is laid over the bottom third so the 48-bar equalizer, which moves with the music, and the thin progress bar stay readable over any picture. If you skip the image, the background is a dark purple gradient with the file name (minus its extension) as the title. Both versions are the kind of still-image video YouTube expects for a music upload.
These come from the converter itself rather than a marketing sheet, so plan around them. The frame size is fixed; if you need 1080p, a vertical 9:16 cut, or shots that change with the song, the AI music video generator renders those from the same audio.
| Spec | Value |
|---|---|
| Resolution | 1280 × 720 (16:9) |
| Frame rate | 30 fps |
| Container and codecs | MP4 (H.264 + AAC) where the browser can record MP4 (Safari, recent Chrome and Edge); otherwise WebM (VP9 or VP8 + Opus), e.g. Firefox |
| Encoding time | Real time: about the length of the song |
| File size limit | None set by Solmi; limited by your device's memory |
| Audio inputs | MP3, WAV, M4A, AAC, OGG, FLAC |
| Image inputs | Any image the browser can open: JPG, PNG, WebP, GIF (first frame) |
| Upload | None: the file stays on your device |
A still image with an equalizer is the right format for a lyric-free upload, a podcast episode, or a quick YouTube post of a track. If the song deserves moving pictures, the AI music video generator storyboards and renders a full video from the same audio, with a consistent performer, lip-sync, and 16:9, 9:16, or 1:1 output; there is a free 20-second 480p preview, and finished renders are on paid plans. For a looping visual rather than a still, the audio visualizer makes beat-reactive clips.
Choose the MP3, press Add image and pick a JPG or PNG (album art, a photo, a poster), then press Create video. The image fills the frame, center-cropped to 16:9, with an animated equalizer and a progress bar along the bottom. Skip the image and you get a dark gradient with the track title instead.
The audio is re-encoded by your browser's video recorder (AAC in an MP4, Opus in a WebM), so it is not bit-identical to the source, but at the bitrates browsers use the difference is inaudible on normal playback. Start from the highest-quality file you have; a 320 kbps MP3 or a WAV gives the recorder the most to work with.
Yes. Open this page in your phone's browser, pick the audio from your files, add a photo from your camera roll, and render. It runs on the phone, so nothing is uploaded, but because it encodes in real time you should keep the screen awake for the length of the song.
Yes. The output is a standard 1280×720, 30 fps video with the audio embedded, which YouTube accepts as is, whether your browser saved it as MP4 or WebM. TikTok and Instagram take the MP4 too; if you got a WebM (Firefox, for example), convert it to MP4 before posting there, or make the video in Safari, Chrome, or Edge. For a vertical TikTok or Reels version, a full AI music video from Solmi can be rendered in 9:16.
Add your audio (and optionally a cover image) and Solmi renders a video with an animated equalizer in your browser. It encodes in real time — roughly the length of your song — so a 3-minute track takes about 3 minutes, with a progress bar. Nothing is uploaded; it all runs on your device.
MP4 where your browser can record MP4: Safari and recent versions of Chrome and Edge. Other browsers, such as Firefox, give you a WebM. YouTube accepts both. For TikTok or Instagram, post an MP4: make the video in Safari, Chrome, or Edge, or convert the WebM to MP4 first.