Pricing
Not listed
Official monthly price not confirmed
- API
- Not confirmed
Voice · Vendor site 2026-10-04
EDGE is a Stanford research project (CVPR 2023) for editable dance generation from music using a transformer diffusion model with Jukebox embeddings. It supports long-form dances via temporal constraints, joint-wise conditioning, in-betweening, and continuation editing.
Researchers and developers exploring controllable dance synthesis rather than SaaS end users.
There is no hosted consumer product or checkout—only academic materials and demos.
EDGE showcases diffusion-based choreography faithful to arbitrary music while supporting spatial and temporal edits for research applications.
What it can do
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Editable generation | Project page describes joint-wise and temporal constraints for dance editing | Facts sourced | 2026-10-04 |
| Jukebox conditioning | Model uses frozen Jukebox embeddings to interpret in-the-wild music | Facts sourced | 2026-10-04 |
| Publication | Site credits CVPR 2023 authors Jonathan Tseng, Rodrigo Castellon, and C. Karen Liu | Facts sourced | 2026-10-04 |
Understand the total cost
Pricing
Not listed
Official monthly price not confirmed
DiffRhythm.ai is a browser AI music generator built on latent diffusion research that creates full songs with vocals and accompaniment from lyrics and style prompts. The site advertises fast non-autoregressive generation up to several minutes, multiple model versions, and credit-based subscriptions plus a limited free quota.
Explore toolTTS.ai is a multi-model text-to-speech platform with 36+ models, 314+ voices, voice cloning, speech-to-text, music, and marketplace listings. The homepage offers free generation without an account while paid plans add commercial licenses, API access, and longer downloads.
Explore toolAudimee is an AI vocal toolkit for music creators. It converts recorded vocals into royalty-free AI voices, supports custom voice training, cover-style vocal generation, harmony making, stem splitting, vocal isolation, and pitch editing from the browser.
Explore toolThe practical questions
EDGE is a Stanford research project (CVPR 2023) for editable dance generation from music using a transformer diffusion model with Jukebox embeddings. It supports long-form dances via temporal constraints, joint-wise conditioning, in-betweening, and continuation editing.
Research demo site with paper and code links; no commercial pricing. This record does not confirm an ongoing free plan.
A listed monthly price has not been confirmed. See the plan cards for entitlements, billing commitments and seat minimums.
Not confirmed. API access and subscription access may have different terms; consult the linked sources.
There is no hosted consumer product or checkout—only academic materials and demos.
No retained pricing changes yet. A current price alone does not establish a historical trend.
Reviewed vendor source
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.