Voice and captions
Captions that land on the word being spoken.
When someone watches with the sound off, the captions are the video. Every word of your narration gets its own start and end time, so the captions follow the voice exactly, and the word being spoken lights up.
Narration per scene
Pick a voice and every scene is narrated in it. Regenerate one scene, change speed and volume, or upload your own recording.
Captions in your style
Presets to start from, then position, font, size, text colour, highlight colour and background box. One style for the whole video.
Fix a word, not the audio
Every word is a chip. Correct a brand name's spelling in the captions or hide a word, without regenerating the voice.
Music cut to length
One background track generated to the length of your video, or upload your own.
Burned in or SRT
Burn the captions into the MP4 on export, and get an SRT file either way.
Your ElevenLabs voices
Optional. Add your ElevenLabs key and every voice in your ElevenLabs account shows up in the voice picker, with previews.
One honest gap
Captions come from narration. Scenes where the speech comes from the clip itself, a dialogue line spoken by the video model or a recorded performance, have no word timings, so they don't carry captions yet.
ElevenLabs is optional. The standard voices run through your AtlasCloud account. ElevenLabs bills you directly, per 1000 characters of narration, if you choose to connect it.
One script, every platform
Captions and voice carry over when you duplicate a video into another format.