Drop an MP4, MOV or WebM clip, up to 10 minutes. ClipNova transcribes the speech word by word, no manual typing, no rewinding.
Choose one of 24 caption styles, like Speech, Hormozi or Karaoke. In most styles, the spoken word lights up in sync with the voice.
Burn the captions into the MP4 for social, or add them as a soft SRT track inside the MP4 that viewers can turn on or off. Your original audio is kept.
The captions are transcribed from this video's voice.
Burned in — drawn into the video, always visible (ideal for social feeds). Words light up one by one in sync with the voice.
Anton, ALL CAPS, thick outline, yellow keyword — the reference.
A tool that transcribes your video and creates word-by-word captions timed to the speech. Pick one of 24 styles, then burn them in or add them as a soft SRT track inside the MP4.
ClipNova transcribes the speech with AI and times every word to the voice. Clear speech with little background noise gives the best results.
The language spoken in your video. ClipNova detects it from the speech, so there is nothing to set.
An MP4 with the captions burned in, or an MP4 with a soft SRT caption track viewers can turn on or off. Burned-in captions always show; a soft track does not show in most browsers.
On paid plans, yes, full commercial rights for monetized videos, ads and client work.
Transcription detects the spoken language on its own and works with many languages, including English, Spanish, French, Portuguese, German, Japanese, Hindi and Arabic.
Find detailed answers to 100+ questions
Type a sentence, ship a video.
Try it out →Upload a photo, get an animated video.
Try it out →Generate from references, consistent every shot.
Try it out →AI hosts with realistic voices.
Try it out →Upload a track, get a beat-synced music video.
Try it out →Join creators turning ideas into scroll-stopping videos, no crew, no software, no learning curve.
