Image + Audio to Video
Combine one still image with an audio file to make an MP4 — the picture is held on screen for the full length of the song or podcast. Perfect for music with cover art or turning a podcast into a video. No upload, works offline — your files stay on your device.
Runs entirely in your browser — your files are never uploaded.
- No upload Your video never leaves your device — it is processed locally.
- Works offline After the first load it runs with no internet connection.
- No size or daily limits No file caps, no paywalls — only your device memory.
- Private & safe Skip sketchy upload sites; nothing is sent to a server.
How it works
The video is built by ffmpeg compiled to WebAssembly and run inside your
browser. The still image is fed in as a looping input (-loop 1) and your audio
becomes the master track; -shortest tells the encoder to stop exactly when the
audio ends, so the video length matches the song or episode. The image is scaled to your chosen
resolution while keeping its aspect ratio, padded to an even size, and encoded to H.264 video
with the audio re-encoded to AAC — the combination that plays on virtually every device and
upload service. Because the picture is static, it is encoded at a low frame rate, which keeps
both the file size and the encode time down. Every step runs on your device, so nothing is
uploaded.
How to turn an image and audio into a video
- Add one still image — a cover photo, artwork or a quote card.
- Add the audio — a song, podcast episode or voice recording.
- Pick a resolution, 720p or 1080p.
- Press Make video and wait — encoding takes time. Then click Download.
The video is as long as your audio, so a full song or podcast episode can take a few minutes to encode on your device, especially on a phone.
Why combine them locally instead of on an upload site
Online "audio to video" tools upload both your image and your full audio track to a server to process, which is slow, hands your files to a third party, and often caps the length or adds a watermark. Doing it in your browser removes the upload step entirely and keeps both files private. It also avoids the safety concerns around free file-handling sites — in March 2025 the FBI warned that some free online tools were being used to spread malware, so keeping the work on your own machine is the safer choice.
| Local (this site) | Typical cloud tool | |
|---|---|---|
| Upload required | No | Usually |
| File-size caps | None (device memory) | Common |
| Works offline | Yes, after first load | No |
| Files stay private | Yes — never sent | Sent to a server |
Common uses
Uploading a track to a video-only platform with your cover art on screen, turning a podcast episode into a video for sharing, posting a beat or demo with artwork, making a simple lyric or quote card with a soundtrack, or sending a long voice note as a video that anyone can play. Because the file compresses well, even a full-length song stays a reasonable size.
More video & audio tools
Frequently asked questions
What is this for?
It turns a single still picture plus an audio file into a standard MP4 video, with the image held on screen for the entire length of the audio. The most common reasons are putting a song online where the platform only accepts video (so you add cover art and upload the MP4), turning a podcast episode into a video for video-first platforms, sharing a voice message or audio note as a video, or making a simple lyric or quote card with a soundtrack. It is the fastest way to get audio onto a video-only service without a full editor.
Are my files uploaded anywhere?
No. The image and audio are read into your browser and combined by ffmpeg compiled to WebAssembly, entirely on your device, and the finished MP4 is written locally for download. Nothing is sent to a server, there is no account, and the engine is cached after its one-time download so it keeps working offline. Your photo and audio never leave your machine.
How long will the video be?
Exactly as long as your audio. The tool loops the still image and uses the audio as the master track, stopping the moment the sound ends, so a four-minute song produces a four-minute video. Because the picture never changes, the video stream compresses extremely well, which keeps the file size reasonable even for a long track.
Why does it take a while for a long song?
Even though the picture is static, the tool still encodes a real H.264 video for the whole duration so the result plays everywhere, and ffmpeg runs as single-threaded WebAssembly rather than native code. A short clip is quick; a long album track or a full podcast episode can take a few minutes, especially on a phone. This is the honest trade-off for keeping everything private and on your device. The image is encoded at a low frame rate since it never moves, which keeps things as fast as possible.
What image and audio formats can I use?
For the image, common formats like JPG, PNG and WebP all work. For the audio, anything ffmpeg can read is fine — MP3, M4A, WAV, AAC, FLAC, OGG and more. The output is always an MP4 with H.264 video and AAC audio, which is the most widely compatible video format for uploading and sharing. If your image has odd dimensions, the tool pads it to an even size so the encoder accepts it.
Can I pick the video resolution?
Yes. You can choose 720p or 1080p. The image is scaled to fit while keeping its aspect ratio and padded with black bars if needed, so it is never stretched. Pick 1080p for a sharp cover image on a large screen, or 720p for a smaller, faster file that is fine for most uploads.
All processing happens on Video Tools entirely within your browser. Your files are never uploaded to a server.