Sora Is Gone: 5 Alternatives That Still Take Your Face (August 2026)
OpenAI retired the Sora app in April 2026 and the API goes dark on 24 September. Here is where the 'me in an AI video' workflow moves, with per-second prices and the real-face policy of each option.
OpenAI wound Sora down in two stages: the app and web experience were discontinued on 26 April 2026, and the API endpoints stop serving on 24 September 2026. If you built anything on Sora 2 or Sora 2 Pro, you have a deadline.
The feature people actually miss is not text-to-video — plenty of models do that. It is putting yourself in the shot. Here is where that goes.
The five that still work
| Option | Endpoint / product | Price | Takes a real face |
|---|---|---|---|
| HappyHorse 1.1 ref2v | alibaba/happy-horse/v1.1/reference-to-video | $0.14/s | yes, up to 9 refs |
| Kling 3.0 Motion Control | fal-ai/kling-video/v3/pro/motion-control | $0.168/s | yes, with likeness limits |
| Wan 2.7 Edit Video | fal-ai/wan/v2.7/edit-video | $0.10/s | yes |
| MiniMax H3 ref2v | minimax/h3/reference-to-video | $0.26/s | yes |
| OmniHuman 1.5 | fal-ai/bytedance/omnihuman/v1.5 | $0.16/s | yes, audio-driven |
Prices read from the live endpoints on 2 August 2026.
HappyHorse 1.1 reference-to-video is the closest thing to the Sora cameo experience: hand it up to nine photos of yourself plus a prompt, get 1080p in a genuine 9:16 or 4:5 frame with native audio and multilingual lip-sync. It is the only one on this list with the full set of vertical aspect ratios out of the box.
Kling 3.0 Motion Control solves a different problem — it copies the movement of a 3–30 second reference clip onto your character. If what you liked about Sora was describing a scene, this is not it. If what you want is to perform someone else's choreography, nothing else on the list competes.
Wan 2.7 edit-video keeps the original video and swaps the performer, so the background, lighting and camera move survive. Cheapest per second of the group and the least talked about.
MiniMax H3, released 31 July 2026, takes up to nine image references plus reference clips for motion and audio, at 2K. It is new enough that there is no meaningful body of user reports yet — treat it as promising rather than proven.
OmniHuman 1.5 is the audio-driven option: a photo plus an audio track produces a performance matched to the audio. Not a scene generator.
What is not a replacement
Seedance 2.0 and Veo 3.1 both refuse real human likenesses, and the filter sits upstream of every reseller — so "use Seedance through a different provider" is not a workaround. If a tool markets itself as a Sora replacement and runs on either of those, it cannot do the cameo use case.
Consumer face-swap apps in the $10–15/month bracket do a narrower job than they imply: most are face-only swaps at 720p with a 15-second cap, which reads as pasted-on rather than as a performance.
Migration checklist
- Note the 24 September API cutoff and inventory anything calling Sora endpoints.
- Decide which of the two jobs you need — new scene from references, or existing clip with a new performer. They are different models.
- Re-check prices before committing. Every number above is dated, and the endpoints reprice without announcement.
- Export anything stored in a Sora account. OpenAI has stated the data goes with the shutdown.