Your voiceon a video without a face
No face on screen: your voice over real stock clips, with captions
A faceless video: my voice over stock clips that fit what I say, with captions and music
Here is the plan:
⚡ Using the skill · Video from stock- Cutting pauses, "umm"s and repeated takes
- Sound effects on the moments
- A natural-voice narration, the best of several takes
Ready. The video is in the project.
What you get
- Stock clips (Pexels) all through the video, a new shot every ~2.4 s
- A scene for every idea, chosen and checked by a cheap model
- The speaker's voice, or an ElevenLabs narration
- Every word on screen the moment it is said
- A hook
- Black title cards
- Sound design
- Music under the voice
- A licence for every shot
What the agent does, in order
- 1A transcript of every word, with its exact time
- 2Cutting pauses, "umm"s and repeated takes
- 3Planning the words on screen, one by one
- 4Gemini watches the video and picks the moments
- 5Sound effects on the moments
- 6Original music that sits under the voice
- 7Finding real stock shots, and checking they fit
- 8One render: the finished video
- 9A natural-voice narration, the best of several takes
The request and the result
Video from stockA faceless video: my voice over stock clips that fit what I say, with captions and music
- “Replace the first shot”
- “A slower pace of shots”
- “A narration instead of my voice”
More skills
Questions
How long does it take?
Usually a minute and a half to five minutes, by the length and the level. You can close the page: the video waits in the project.
Can I fix it afterwards?
Yes. Write in the chat what to change and a new version comes out. The previous one is kept and you can go back to it.
Which language does it work in?
In Hebrew, and in any language spoken in the video. The captions come out in the language of the speech.
What about rights to the stock and the music?
The stock comes from free libraries, with a licence for every shot. The music is made new for every video, so it is yours.