videoavailableverified

OmniHuman 2.0

ByteDance (BytePlus)

Talking-head / digital-human videos from one image plus an audio track, up to 5 minutes.

Data basis

Input → Output

image, audio, text → video

Pricing unit

USD / second

Access

cloud-api

Last verified

2026-10-18

Pricing and verification

$0.07 / second

Price status: Priced
Verified: 2026-10-18

BytePlus (international) list price $0.07/s, native 720p, 30–300 s output. Volcengine (China) CNY price not published on the public Ark pricing page as of 2026-10-18; not listed. License: commercial API only, no open weights.

Model performance benchmarks

No audited, comparable public benchmark score is available yet. Music and world models do not currently have a unified public leaderboard; video models are seeded from public sources such as VBench / VBench++ where available.

Capabilities

audio-driven avatar videolip syncmulti-person scenestext prompt controlAPI

Pricing and plans status

BytePlus official API: $0.07 per second of output video (OmniHuman 1.5: $0.12/s)

Note: multimodal pricing can be seconds, generations, credits, minutes, plan allowances or enterprise contracts. It is not forced into token pricing; only verified source-backed rows appear below.

Pricing sources and usage units

No structured pricing reference row yet; showing official pricing unit and source links above.

Related plans

No mapped plan yet. Next step is to materialize plans for Runway, Kling, Pika, Luma, Suno, Udio and similar providers.