Sometimes the goal isn't to layer sound on top of what's there — it's to get rid of it. Bad on-set audio, an unwanted ambient track, a placeholder scratch voiceover: attach_audio_to_video's mode 'replace' strips the video's original audio entirely and substitutes whatever you supply.
This is the same tool as add-music-to-video and add-voiceover-to-video, just the other mode. If you want to keep some of the original sound and add to it, use mode 'mix' on those pages instead.
Powered by
Attach an audio file to an existing video. Use when the user has a generated/uploaded video AND a separate audio track (music, voiceover, SFX, generated speech) and wants them combined. Two modes: (A) 'replace' (default) — strips the video's original audio and substitutes the supplied audio. Pick this when the user says 'replace the sound', 'mute the original', 'put this music on the video', or any time the supplied audio should be the only audible track. (B) 'mix' — keeps the original video audio AND mixes the new audio on top, with separate volume controls. Pick this when the user wants background music UNDER existing voice/SFX (e.g., 'add background music', 'put music behind my talking video'). Video stream is copied losslessly (no re-encode of visuals). Fast. Costs a flat credit fee regardless of length.
What to tell the agent
Versely's agent maps this plain-English request directly onto attach_audio_to_video. You don't need to know the parameter names — just describe what you want.
“Replace the audio on this video entirely with this new voiceover track — mute the original completely.”
How it works
1. Prepare the replacement audio
This can be a generated voiceover, a generated or uploaded music track, or any HTTPS audio URL.
2. Set mode to 'replace'
This is the default mode on attach_audio_to_video — it strips the video's original audio and substitutes the new file.
3. Optionally trim
trim_to lets you cap the output to match the new audio's length if it's shorter than the source video.
4. Render
The video stream is untouched (no visual re-encode); only the audio track changes.
What it costs
Flat credit fee regardless of the video's length — the same pricing as the 'mix' mode use cases above.
The formula behind that number: What does an AI video with sound cost? — flips the per-second rate with an audio toggle rather than adding a separate fee.
Limits & things to know
- This fully mutes the original — there's no partial ducking or fade-out of the old track (that's what 'mix' with a low original_volume is for).
- The replacement audio needs to already be an accessible HTTPS URL — file:// paths and other local schemes are rejected.
Who uses this
- Fixing bad on-set audio
- Swapping a scratch voiceover for the final read
- Muting copyrighted background audio before reposting a clip
- Turning silent B-roll into a fully voiced edit
Frequently asked questions
Does this keep any of the original sound?+
No — mode 'replace' strips the video's original audio entirely and substitutes the new track you provide. If you want to keep some of the original, use mode 'mix' instead (see add-music-to-video).
Does replacing the audio affect video quality?+
No — the video stream is copied losslessly; only the audio track is swapped.
Can the new audio be shorter than the video?+
Use the trim_to parameter to cap the output length to match, if needed.
Related Versely tools
Related editing jobs
Replace the Audio in a Video inside Versely
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.