Build with Audio Tempo.
Change the speed of an audio clip from 0.5x to 2x with the PITCH PRESERVED (ffmpeg atempo), so a voice line gets faster or slower without turning into a chipmunk.
Best for
Change the speed of an audio clip from 0.5x to 2x with the PITCH PRESERVED (ffmpeg atempo), so a voice line gets faster or slower without turning into a chipmunk. Use the playground to set up a single step, then open a workflow when you want to connect more tools.
Inputs explained
- Audio (required)
- Set the audio used by this model. Type: audio.
- Mode (optional)
- Set the mode used by this model. Type: text. Options: factor, target_seconds. Default: "factor".
- Speed (0.5 to 2; blank = 1x) (optional)
- Set the speed (0.5 to 2; blank = 1x) used by this model. Type: number. Default: 1.
- Target seconds (Target mode) (optional)
- Set the target seconds (target mode) used by this model. Type: number.
- Format (optional)
- Set the format used by this model. Type: text. Options: mp3, wav. Default: "mp3".
Tips before you run
Start with the default settings and change one input at a time. Keep the result you like on your board so the next step can use it.
If you add a reference file, use a link the workflow can read. Check the inputs and credit estimate on the board before starting a run.
Working with this model
What it is for
A voice line runs 0.4 seconds long for the shot. Speed it up to 1.1x and it fits,
with the pitch unchanged. ffmpeg's atempo retimes without resampling the
voice up, so it sounds faster, not higher.
Re-voicing a reel with a new voice clone? Each new phrase comes out a little longer or shorter than the lip-sync take it has to land on. Set Mode to Target seconds, type the take's length, and the node measures the phrase and picks the speed for you (source length / target).
Settings
- Mode: Factor (default) reads Speed. Target seconds reads Target seconds and ignores Speed.
- Speed is 0.5 to 2, >1 is faster and shorter. Blank or 1 hands the input through untouched (no transcode).
- Target seconds (Target mode): the length to land on. The speed it needs must also be 0.5 to 2, so a 2.2s phrase fits anywhere from 1.1s to 4.4s. The source is measured from the file (wav, mp3 and m4a); an unreadable one is refused, not guessed.
- Format is mp3 (default) or wav. Sample rate and channels are kept from the source.
Anything outside the range is refused with the numbers, never clamped.
Outputs
Audio is the retimed clip. Duration is its measured length in seconds, read from the output file, so you can wire it into anything that needs the real number.
Free, and why
The node is in the free set: it re-runs whenever something downstream runs, and it has no Run button. The output file is named by a hash of the input url and the settings, so an unchanged re-run reuses the last file and invokes nothing. Change the speed and it makes a new file.
Common questions
How do I use Audio Tempo on Wireflow?
Set the inputs above and choose Open in a workflow. Sign in to save your board, then check its credit estimate before you run.
Can I use Audio Tempo through an API?
Yes. Save a workflow with this model, then call the Wireflow run API with its workflow ID. The API tab has examples you can copy.
What changes the credit price?
The price shown uses the model defaults. Your inputs and model settings can change the total. The workflow shows an estimate before you run.
Can I connect this to another model?
Yes. Open it in a workflow and connect its output to another node with a matching input type.