Feature · Available on Creator and Studio plans
AI Avatar Videos
Generate a talking-head video from a transcript — no camera, no recording session. HeyGen presenter plus your script.
HeyGen
Provider — premium talking-head generator, BYOK
1500
Character limit per script (≈3 minutes of video)
≈ 2min
From submit to rendered video URL
HeyGen talking-head \u00b7 script \u2192 MP4
“This week we shipped Viral Moments \u2014 drop a 60-minute recording and get the 5 clips worth posting, scored and captioned\u2026”
When this makes sense
Not every video needs you on camera.
Weekly "what shipped" recaps, product-release announcements, quick explainers — there’s a class of video where the message is the content and the face is just a delivery mechanism. AI Avatar replaces the recording session without losing the talking-head format.
How it works
Script goes in, MP4 comes out.
From any content item, open Tools → AI Avatar. The script defaults to the first 1500 characters of your transcript or a draft. Pick a HeyGen stock presenter (or upload your own licensed avatar image later), hit Generate. HeyGen synthesizes audio, lip-syncs it to the presenter, and returns a 1080p MP4 in about 2 minutes. The video drops into your content library ready for the Viral Moments pipeline if you want clips out of it.
- Stock HeyGen presenters — diverse set, no additional licensing needed
- BYOK HeyGen key — pay them directly, no Clipflow markup
- Works off any content item that has a transcript or draft
- Output flows into the standard render + subtitle pipeline
Why Studio only
HeyGen calls are expensive relative to other AI features.
Even on BYOK, a 2-minute AI Avatar render costs ~$0.50–1.00 on HeyGen’s API. Gated to Studio so the infrastructure cost on our side (webhook handling, storage, retry queue) is covered by the plan price. If you only need this occasionally, a month of Studio is cheaper than a single on-camera shoot.
Works well with
Auto-Dub (Multi-language)
Translate and dub your video into Spanish, German, French, Portuguese, Japanese, Korean, o…
Auto-Subtitles
Word-level karaoke captions burned into every clip — TikTok Bold, Minimal, Neon, or White …
Brand Voice
Captions that sound like you, not like a template bank. Learned from your own past posts.
Frequently asked
Do I need a camera to make an AI Avatar video?
No. You paste a script or pull one from a Brand Voice draft, pick a HeyGen presenter, and Clipflow generates a 1080p talking-head video with lip-synced audio in about two minutes — no recording session.
Which plan is AI Avatar on, and how is it billed?
It is available on the Creator and Studio plans. AI Avatar is BYOK: you bring your own HeyGen key and pay HeyGen directly at their rates, with no Clipflow markup.
Can I make clips out of an avatar video?
Yes. The rendered video drops into your content library and flows into the standard Viral Moments render and subtitle pipeline, so you can clip and caption it like any other upload.
Try AI Avatar Videos on your next recording.
Free tier, no credit card. Your first draft lands in about two minutes.
Start free — no card