GIVON AI
← All models

OmniHuman 2

Animates one character image from speech or singing, synchronizing lip movement, expressions and gestures. Creates a continuous video from 4 seconds to 5 minutes, with optional performance and camera direction.

Cost

10 tokens/s

VideoProvider: Bytedance

Try OmniHuman 2 in Givon AI

Open a working project for regular creation, or use Playground to inspect the model parameters.

Create in a projectOpen in playgroundUse through API

Use through API

Request fields, constraints, and ready-to-use examples for developers. The user workflow starts above.

Run generation
IDEMPOTENCY_KEY="${IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.givon.ai/api/v1/generations \
  -H "Authorization: Bearer $GIVON_API_KEY" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"video","model":"omnihuman-2","input":{"prompt":"cinematic drone shot over a city at night","speakerImage":"asset://asset_...","speechAudio":"asset://asset_..."}}'

Input fields

* required
promptprompt

Performance direction such as emotion, pace and delivery.

Type
string
Default
—
Allowed
string
Speaker image*speakerImage

Asset input for the speakerImage slot.

Type
string
Default
—
Allowed
image · asset, https, data
Speech audio*speechAudio

Asset input for the speechAudio slot.

Type
string
Default
—
Allowed
voiceover · asset, https, data

Cost

10 tokens/s

Capabilities

Modesimage_to_video
Asset slotsspeakerImage:image*speechAudio:voiceover*
Get API key

Where to use this model

AI video generatorImage to video