Which should you pick?
LTX 2.3 Audio to Video and HeyGen Image to Video start at the same 50 credits for a complete generation.
At their most expensive settings the gap widens: HeyGen Image to Video tops out at 1200 credits a job versus 200, driven by clip length.
HeyGen Image to Video supports more aspect ratios (6: 16:9, 5:4, 1:1, 4:5, 9:16, auto), giving it more format flexibility.
HeyGen Image to Video requires a starting image; LTX 2.3 Audio to Video can generate from a text prompt alone.
What a job costs
LTX 2.3 Audio to Video
50-200 credits
It bills per second of output, and the price moves with clip length.
- Price10 credits
HeyGen Image to Video
50-1200 credits
It bills per second of output, and the price moves with clip length.
- Price10 credits
All figures are Versely credits. Your plan's credit allowance is on the pricing page.
Spec comparison
| Spec | LTX 2.3 Audio to Video | HeyGen Image to Video |
|---|---|---|
| Provider | LTX | HeyGen |
| Cost per job | 50-200 credits | 50-1200 credits |
| Billing | per second of output | per second of output |
| Max resolution | 1080p | 1080p |
| Aspect ratios | auto, 16:9, 9:16 | 16:9, 5:4, 1:1, 4:5, 9:16, auto |
| Durations | — | — |
| Frame rates | — | — |
| Qualities | — | 1080p, 360p, 480p, 540p, 720p |
| Requires starting image | No | Yes |
| Accepts video input | No | No |
| Reference images | — | — |
| Leaderboard | Unranked | Unranked |
| Released | Mar 5, 2026 | Sep 15, 2024 |
What each one does that the other doesn't
Only LTX 2.3 Audio to Video
fast, high quality, stylized, lipsync, audio driven
Only HeyGen Image to Video
photo avatar, custom image, multi voice, expressions
Both list: audio to lipsync.
Full LTX 2.3 Audio to Video spec sheet →
High-quality, fast AI video model for audio-to-video with lipsync, stylized transform capabilities
Full HeyGen Image to Video spec sheet →
Turn your photo into a talking avatar video. Upload a selfie and choose a voice — HeyGen Avatar 4 generates realistic lip-sync video.
Frequently asked questions
Which is cheaper, LTX 2.3 Audio to Video or HeyGen Image to Video?+
Neither — both start at 50 credits for a complete generation on Versely.
What can LTX 2.3 Audio to Video do that HeyGen Image to Video can't, or vice versa?+
Only LTX 2.3 Audio to Video lists fast, high quality, stylized, lipsync, audio driven. Only HeyGen Image to Video lists photo avatar, custom image, multi voice, expressions. Both list audio to lipsync.
How do LTX 2.3 Audio to Video and HeyGen Image to Video bill?+
LTX 2.3 Audio to Video bills per second of output, and its price moves with clip length. HeyGen Image to Video bills per second of output, and its price moves with clip length. Both are charged in Versely credits.
Try both inside Versely
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.