ByteDance · fal.ai · Talking avatar from an image and an audio track
OmniHuman 1.5
OmniHuman 1.5 (ByteDance), talking avatar from an image and an audio track, served by fal.ai. The OpenAPI schema for the fal-ai/bytedance/omnihuman/v1.5 queue. Price: $0.16 per second of output video, which follows the audio length, metered by fal after the call (x-fal-billable-units) and billed at that reading; the reservation is the bound you declare and the difference is refunded. Asynchronous: returns a request_id; poll fal/status and fetch fal/result with model "fal-ai/bytedance".
$0.16 / unitfal.aiVideofal/omnihuman-1-5Listed
Activation pending; your agent will see it as unavailable until then.
Use this tool with your agent
Use my connected Agentik MCP server. I want to use the tool fal/omnihuman-1-5 (OmniHuman 1.5 (ByteDance), talking avatar from an image and an audio track). Call inspect_tool with {"tool_id": "fal/omnihuman-1-5"} first and tell me the price before anything runs. Ask me for the inputs it needs; never invent values, IDs or file URLs. When I confirm, call run_tool with tool_id "fal/omnihuman-1-5" and my inputs, follow it with get_run if it is still running, and give me the result and the price Agentik reports. If the tool is unavailable, say so and use discover_tools to propose an alternative.Show the prompt
Paste it into Claude, ChatGPT or Codex: your agent takes it from there, and shows the price before it runs.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
resolution | string | No | The resolution of the generated video. Defaults to 1080p. 720p generation is faster and higher in quality. 1080p generation is limited to 30s audio and 720p generation is limited to 60s audio. Options: 720p, 1080p. |
audio_url | string | Yes | The URL of the audio file to generate the video. Audio must be under 30s long for 1080p generation and under 60s long for 720p generation. |
mask_url | string | No | The URL of the mask image to apply to the image. Only the person in the white area of the mask will speak. |
image_url | string | Yes | The URL of the image used to generate the video |
prompt | string | No | The text prompt used to guide the video generation. |
turbo_mode | boolean | No | Generate a video at a faster rate with a slight quality trade-off. |
max_seconds | number | No | Upper bound of the output video length, which follows the audio, in seconds (default 30, max 600). The reservation is this bound at the unit price; after the call the seconds fal meters are billed and the rest is refunded. Declare at least the real amount: a larger input is still processed but is never billed above the reservation. |
How your agent calls it
First inspect_tool for the current schema and price, then run_tool with the published example after confirming your inputs:
{
"tool_id": "fal/omnihuman-1-5",
"input": {
"image_url": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_image.png",
"audio_url": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_audio.mp3",
"resolution": "720p",
"max_seconds": 15
}
}Price and billing
- Price
- $0.16 / unit
- Model
- Per unit
- Detail
- The provider’s price, with no markup. Billed for measured usage.
- The provider’s price, 0% markup.
- One prepaid balance for every provider; your agent sees the price before it runs.
- Pay for measured usage; unused reservations are released.