Which should you pick?
LTX 2 Audio to Video is the cheaper job: 16 credits against 40-128 credits for Wan 2.2 Speech Turbo. Those are the credits one complete generation costs, not a headline rate, so they are directly comparable even though the two models bill differently.
At their most expensive settings the gap widens: Wan 2.2 Speech Turbo tops out at 128 credits a job versus 16, driven by output resolution.
Wan 2.2 Speech Turbo requires a starting image; LTX 2 Audio to Video can generate from a text prompt alone.
What a job costs
Wan 2.2 Speech Turbo
40-128 credits
It bills per second, at a rate that changes with output resolution, and the price moves with output resolution.
- SD8 credits
- HD/4K16 credits
LTX 2 Audio to Video
16 credits
It bills a flat rate per generation.
- Price16 credits
All figures are Versely credits. Your plan's credit allowance is on the pricing page.
Spec comparison
| Spec | Wan 2.2 Speech Turbo | LTX 2 Audio to Video |
|---|---|---|
| Provider | Wan | LTX |
| Cost per job | 40-128 credits | 16 credits |
| Billing | per second, at a rate that changes with output resolution | a flat rate per generation |
| Max resolution | 1080p | — |
| Aspect ratios | — | — |
| Durations | — | — |
| Frame rates | — | — |
| Qualities | 480p, 580p, 720p | — |
| Requires starting image | Yes | No |
| Accepts video input | No | No |
| Reference images | — | — |
| Leaderboard | Unranked | Unranked |
| Released | Aug 27, 2025 | Jan 6, 2026 |
What each one does that the other doesn't
Only Wan 2.2 Speech Turbo
image to lipsync, fast, natural, high quality, efficient, speech driven
Only LTX 2 Audio to Video
audio to video, audio visualization, music video
Both list: audio to lipsync.
Frequently asked questions
Which is cheaper, Wan 2.2 Speech Turbo or LTX 2 Audio to Video?+
LTX 2 Audio to Video is cheaper per job: 16 credits against 40-128 credits for Wan 2.2 Speech Turbo.
What can Wan 2.2 Speech Turbo do that LTX 2 Audio to Video can't, or vice versa?+
Only Wan 2.2 Speech Turbo lists image to lipsync, fast, natural, high quality, efficient, speech driven. Only LTX 2 Audio to Video lists audio to video, audio visualization, music video. Both list audio to lipsync.
How do Wan 2.2 Speech Turbo and LTX 2 Audio to Video bill?+
Wan 2.2 Speech Turbo bills per second, at a rate that changes with output resolution, and its price moves with output resolution. LTX 2 Audio to Video bills a flat rate per generation. 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 your browser or on your phone.
Free on the web and on iPhone, one account.