Free tool Nothing saved or uploaded
UGC script timer
Paste the words you’ll say on camera and see how long they take to say, and whether the script fits a 15, 30, 45 or 60-second video. Nothing is saved or uploaded.
0 words
Paste only the words you’ll say on camera. Leave out shot notes and captions. Your script stays in this browser and is not saved.
How the script timer works
The timer divides your word count by your speaking pace. At 150 words per minute, 75 words take 30 seconds. Pick a target to see how many whole words fit at that pace.
seconds = words × 60 ÷ words per minute
word budget = floor(target seconds × words per minute ÷ 60)
| Target speaking time | Word budget |
|---|---|
| 15 seconds | 37 |
| 30 seconds | 75 |
| 45 seconds | 112 |
| 60 seconds | 150 |
These are planning options, not platform limits. You don’t need to fill every spare second.
Why 150 words per minute
Voices’ words-to-time guidance describes conversational US English at around 150 words per minute and gives a typical range of 120–150. Accent, delivery and the script all affect it. We use 150 as a practical starting estimate, not a measured UGC average or the right pace for everyone.
Source checked . Speaking pace is different from silent reading and typing speed. If you know your own delivery, open “Adjust speaking pace” and enter it.
Speaking time isn’t video length
Pauses, emphasis, B-roll, demonstrations and transitions can all add time. Punctuation and line breaks don’t add pauses in this model. Time a read-through, including the actions you plan to film, before you record.
How words are counted
Spaces, tabs, line breaks and em or en dashes separate words. A piece of text counts if it contains a letter or digit. Contractions such as “don’t” and hyphenated terms such as “self-care” each count as one word. Punctuation, symbols and emoji on their own count as zero.
Numbers, currency, dates, acronyms and URLs count as one written token each, but may take several words to say. Write “twenty-nine dollars” rather than “$29” for a closer estimate. Bracketed text such as [show product] is counted: remove stage directions and paste only spoken copy. Each line you type is timed separately; visual wrapping changes nothing.
Built for English scripts, not accurate for languages written without spaces between words. The limit is 20,000 UTF-16 characters (an emoji can use two); longer text is kept but not timed.
Common questions
How many words is a 30-second script?
At 150 words per minute, 75 words take 30 seconds. The whole-word budgets are 37 for 15 seconds, 112 for 45 and 150 for 60. These are formula outputs, not ideal script lengths. Your own pace may differ, so time a read-through.
How fast do people talk?
Voices puts conversational US English at around 150 words per minute and gives a typical range of 120–150, depending on accent, delivery and script. This is guidance, not a universal average or a measurement of UGC creators. Speaking is different from silent reading, and typing-speed tests measure keystrokes, not spoken delivery.
Why is my finished video longer than the estimate?
Pauses, emphasis, demonstrations, B-roll and transitions add time that has no spoken words. The timer estimates only speaking time. Time one read-through with the actions you plan to film before you record.
Does the timer save or upload my script?
No. It runs in your browser. Nothing is saved, sent or added to the page address. Clearing the box removes the script from the tool; your browser may keep its own native undo history.
How are words counted, and does it work in other languages?
Text is split at spaces, line breaks and em or en dashes. Each piece containing a letter or digit counts as one word; contractions and hyphenated terms stay together. Punctuation and emoji alone count as zero. Numbers, currency, dates, acronyms and URLs count as written tokens, so write them out as spoken for a closer estimate. Bracketed stage directions are counted too. This is built for English and is not accurate for languages written without spaces between words.