OmniHuman 2 is ByteDance's audio-driven human video model. It turns one image of a person and an audio track of 4 to 300 seconds into a video whose expressions, gestures, and movement follow the audio, with an optional prompt to direct the scene.
$0.0525
How long a clip takes over every route we serve it from: from the accepted job to the finished video.
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Length of video generated per day on NagaAI, counted since November 2026.
OmniHuman 2 is ByteDance's audio-driven human video model. It turns one image of a person and an audio track of 4 to 300 seconds into a video whose expressions, gestures, and movement follow the audio, with an optional prompt to direct the scene.
On NagaAI, OmniHuman 2 costs $0.0525 per second. You pay only for what you use, with no subscription.
It takes text, images and audio as input and returns video.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI SDK pointed at NagaAI. The API section on this page has a ready example.
Not enough activity data to display a chart
Not enough data yet