How to Add Voice Cues to a HIIT Workout Video in 5 Minutes
Short answer: Once your exercise clips are in Fit Cut Pro, voice cues take about five minutes: record (or generate) the ten trainer cues once, give each exercise clip a spoken name of up to 4 seconds, switch voice cues on in the Voice side tab and export. From then on every HIIT workout built from those clips talks on its own: “Get ready”, the first exercise and a spoken “3, 2, 1, Go” at the start; “Rest”, “Next” and the next exercise’s name in every rest; “Halfway” in sets of 30 seconds or longer; “Well done” at the end. Recording your lines is free on every plan and the trial; AI voice lines need a paid plan and cost 1 AI credit per started 250 characters.
How it works
- 1
Have your clips in the library (0 minutes if they already are)
Upload one short clip per exercise in Clips and name it after the move: Jumping lunges, Mountain climbers, Burpees. Use the same words in its spoken Name line, so what people see and hear match.
- 2
Open the Voice studio (10 seconds)
In the Creator, open the Voice side tab. The Voice studio card has three rows, Voice, Trainer cues and Exercises; each opens the studio on that tab.
- 3
Record the trainer cues (about 2 minutes)
On the Trainer cues tab, click Produce on each cue and Record it: Next, Rest, Get ready, 3, 2, 1, Go, Halfway, Last round and Well done. On a paid plan, pick a stock AI voice on the Voice tab and click Set up basic cues with this voice instead: every missing cue is created at once, for free.
- 4
Give every exercise a spoken name (about 2 minutes)
On the Exercises tab, open each clip and Record its Name: two or three words, under 4 seconds. Or pick a voice and click Voice all exercise names: one AI request covers every clip that has no name line yet.
- 5
Switch cues on, preview and export (about 1 minute)
Turn on Voice cues in my videos and Voice cues in this workout, choose which cue types play, press play in the Creator preview to hear the cues live, and export.
What a 40/20 HIIT round sounds like
Take a classic circuit: eight exercises, 40 seconds of work and 20 seconds of rest, three rounds. The video opens with “Get ready”, then “Jumping lunges” (the first exercise, without “Next”), then “3, 2, 1, Go” as the first set starts.
At the end of each set the beep opens the rest. You hear “Rest”, then “Next”, then “Mountain climbers”, and the usual 3-2-1 beeps lead into the set. Halfway through each 40-second set the voice says “Halfway”. In the rest before the third round, “Last round” comes before “Next”. After the final set, “Well done”.
The music dips under every line and comes back after it, so the cues stay clear over a loud track. Nothing is placed on a timeline: change the plan to 45/15 or swap an exercise and the cues follow.
Short rests and Tabata-style timing
HIIT often uses short rests, 10 or 15 seconds, and a rest never talks over its own 3-2-1. When the lines do not fit, Fit Cut Pro drops them in a fixed order: “Rest” first, then “Last round”, then “Next”. The exercise name is kept to the end, because knowing what comes next is what lets people get into position.
Keep names short for short rests. “Burpees” fits anywhere; “Burpee with push-up and tuck jump” may cost you the “Next” in a 10-second rest. The Name slot holds up to 4 seconds; under 2 is ideal for HIIT.
Add form tips where they matter
Each clip also has an Info line: a form tip of up to 15 seconds, played once per workout at that exercise’s first set, so it never repeats every round. Use it for the two or three moves people get wrong: “Land soft, knees out, chest up” for squat jumps, “Hips level, shoulders over wrists” for mountain climbers.
On Pro and Ultimate, the ✨ button in the Info line writes the tip for you in your app language, sized to fit 15 seconds, for free (no credits). Read it, adjust it, then record it yourself or generate it in an AI voice.
Record yourself, upload or use an AI voice
Record in the browser: press Record, wait for the 3-2-1 and speak; replay and re-take until it sounds right, then click Use this. Silence is trimmed and the volume normalised automatically. A quiet room and a normal coaching voice work better than shouting.
Upload if you already have the lines from a recording session: MP3, M4A, WAV or similar, up to 15 MB per file.
AI voice: type the line, pick a voice and click Generate; listen and click Use this or Try again. There are natural multilingual voices and native-speaker voices for your app language, and on Pro and Ultimate you can create an AI voice from your own by reading a script of about 90 seconds once, after a consent step.
A HIIT class you filmed: the AI Editor
If you filmed the whole class in one take, upload it to the AI Editor instead. It finds every exercise and rest, adds the timers, and your clip lines play when a clip’s name matches the detected exercise name; the announcement plays when the next-exercise window appears. Your own coaching audio dips under each cue. In the Editor, voice cues are switched on per project, and Info and the spoken countdown are off by default.
What it costs
Recording and uploading are free on every plan, the 14-day trial included. AI voice lines need Starter ($49.99 per month), Pro ($99.99) or Ultimate ($199.99) and cost 1 AI credit per started 250 characters per request; the trainer cues in a stock AI voice are free. Plans include 30, 100 or 300 AI credits a month, shared with FIT AI images and videos. A whole HIIT library of eight to twenty exercise names usually fits in a few credits.
Frequently asked questions
- Do I have to redo the cues for every new HIIT workout?
- No. Lines belong to the clips and the trainer cues are shared, so every new workout built from the same clips speaks straight away.
- Does the spoken countdown replace every 3-2-1?
- No. “3, 2, 1, Go” is spoken only at the start of the workout; every later rest and set keeps the 3-2-1 beeps.
- Can I turn off “Halfway” or the form tips for one video?
- Yes. In the Voice side tab choose which cue types play (Rest, Next + exercise name, Exercise info, Countdown voice, Extras), or turn voice cues off for that workout.
- Does it work in portrait videos for Instagram and TikTok?
- Yes. Voice cues are part of the audio, so they play in any orientation you export.