Podcast clipper
Scenario. Repurposes 90-min podcasts into vertical clips for TikTok and Reels.
Outcome. Captions burn in with the right safe-zone for each placement, in one render.
Auto Captions
Captions that look native to every platform.
Word-timed AI transcription, animated word-by-word, styled to match your brand and sized for each platform's safe zones.
- OpenAI Whisper transcription with word-level timing
- Per-platform safe-zone awareness (Reels, Shorts, TikTok, LinkedIn)
- Brand-template fonts, colors, and animation presets
- Edit any word with a single click; positioning auto-rebalances
- Multilingual: 60+ languages auto-detected
How Auto Captions works
- 01
Add captions
One click on any clip with audio.
- 02
AI transcribes
Whisper produces word-timed captions in seconds.
- 03
Pick a brand template
Apply your saved style — font, color, motion preset, position.
- 04
Refine if needed
Click any word to fix it; the timing adapts automatically.
Who uses it
Course creator
Scenario. Needs SRT files for accessibility plus burned-in captions for Reels.
Outcome. Both export options available from the same caption track.
Travel vlogger
Scenario. Records in three languages on the same trip.
Outcome. Whisper auto-detects each clip's language; per-clip styling stays consistent.
Auto Captions questions, answered
What's the transcription accuracy?+
OpenAI Whisper-large is industry-leading on clean audio. Heavy accents or background noise reduce accuracy — you can fix any word in one click.
Can I export captions as SRT or VTT?+
Yes — both formats. Use them for YouTube uploads, accessibility compliance, or downstream tooling.
Does it handle multiple speakers?+
Yes — speaker diarization is on for podcast and interview workflows. Each speaker gets a labelable lane.
Which languages are supported?+
60+ via Whisper. Detection is automatic — no need to set a language flag manually.