Creator
Billed monthly
For solo creators posting every week
500 credits every month
- Up to 250 AI images
- Up to 50 Studio exports, plus the first export of each project
- Up to 1.5 hours of AI voiceover
- Roll over up to 1,000 credits
Every word on screen as it's said.
Add your video to Studio and Auto captions writes each spoken word onto the timeline at the moment it is said. Fix any word, pick a style, and export with the captions burned in.
Free: caption it in an app on your phone or computer, or let YouTube do it. Studio is the paid route, for word-by-word styles burned into the video.
Steps from each maker's help page: Instagram Edits, Microsoft Clipchamp, YouTube.
Studio runs in a desktop browser, on plans from $19 a month. Auto captions costs nothing extra, and each project's first export is included. It takes up to 45 minutes of audio per run, and Studio exports the video itself, not an SRT or VTT file.
Open Studio on a computer and add your video or audio file. It lands on the timeline.
Open the Captions tab and press Auto captions. Each word lands on the timeline at the moment it is said.
Play the video and fix what needs fixing. Edit a word, split or merge a caption, or drag it to change when it shows.
Choose one of 31 styles, set how many words show at a time, and export. The captions are part of the video.
Auto captions gives every word its own start and end. That is what lets a style light up the word being said. This is the sentence from the top of the page, as Auto captions timed it.
0.00 s of 5.95 s
Each style here is drawn from its Studio preset: the font, the colors, the outline and how many words show at once. Pick one to hear the line in it.
Dynamic: Heavy capitals, three words at a time, the spoken word in pink.
A bike mechanic's tip, with numbers, units and an Irish name. Auto captions heard all 17 words. This is what it wrote:
Tyres to 80 psi, stem bolts to five Newton meters. If the Presta valve sticks, ask Shiban
Tyressaid “tires”
The British spelling. Right as written, unless you write for a US audience.
Right as written
80 psi,said “eighty PSI”
The number came back as digits and the unit in lower case.
Worth an edit
five Newton meters.said “five newton meters”
This number stayed a word, so the line mixes 80 and five. Newton came back capitalized.
Worth an edit
Presta valvesaid “presta valve”
Capitalized, the way the valve name is usually written.
Right as written
Shibansaid “Siobhan”
The name came back as Shiban, spelled the way it sounds in the clip.
Worth an edit
Every word was there. The name came back the way it sounded, and the numbers were not written the same way. Read the captions through before you export, and check names, numbers and units against the way you write them.
Auto captions works out the language from the audio. There is no language to pick. We filmed a ramen cook's line in four languages and captioned each one. Every word came back as it was said.
English, as Auto captions wrote it
We open at nine on Saturday. Come early, the ramen sells out fast
It writes what was said, the way it was said: the hour came back as a word in all four. It does not translate.
Open captions are part of the picture. Closed captions are a separate file that the player shows when the viewer asks for it.
What Sceneform makes
Not in Sceneform
Pick the plan for how much you post. Every model on every plan. Unused credits roll over. Cancel anytime.
Billed monthly
For solo creators posting every week
500 credits every month
Billed monthly
For creators posting daily across channels
1,300 credits every month
Billed monthly
For brands and production teams
2,700 credits every month
Billed monthly
For agencies running always-on content
5,500 credits every month
Want checkout, comparison tables, or a custom volume? See the full pricing page

Plans from $19 a month. Commercial use included.