# OmniHuman 1.5 talking avatar from image and audio

Needs image url and audio url. Served by fal.ai.

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; fal accepts at most 30 s of audio at 1080p and 60 s at 720p, so $4.80 (1080p) or $9.60 (720p) is reserved, metered by fal after the call (x-fal-billable-units) and billed at that reading; the reservation is the provider's documented maximum for one request and the difference is refunded. Asynchronous: returns a request_id; poll fal/status and fetch fal/result with model "fal-ai/bytedance" and that request_id. Billed once, when the result is ready; a generation that fails is refunded.

- Tool ID: `fal/omnihuman-1-5`
- Name in the catalog: OmniHuman 1.5 (ByteDance), talking avatar from an image and an audio track
- Provider: [fal.ai](/providers/fal.md)
- Capability: [Talking avatar (OmniHuman)](/tools/video-generation/talking-avatar.md)
- Price: usage based, the maximum is shown before a run
- Authentication: an authorised Agentik workspace is required for execution, including zero-price tools.

## Pricing contract

The provider’s price, with no markup. Billed for measured usage.


```json
{
  "model": "per_unit",
  "amountUsd": 0.16,
  "unitsHeader": "x-fal-billable-units",
  "maxUnits": 30,
  "fractional": true,
  "unitsPath": "duration",
  "unitsHeaderUsd": 0.16,
  "multipliers": [
    {
      "when": {
        "field": "resolution",
        "equals": "720p"
      },
      "factor": 2
    }
  ]
}
```

Pricing source: [https://fal.ai/models/fal-ai/bytedance/omnihuman/v1.5](https://fal.ai/models/fal-ai/bytedance/omnihuman/v1.5). $0.16 per second of output video, which follows the audio; fal accepts at most 30 s of audio at 1080p and 60 s at 720p, so $4.80 (1080p) or $9.60 (720p) is reserved, metered by fal after the call (x-fal-billable-units) and billed at that reading; the reservation is the provider's documented maximum for one request and the difference is refunded..

Price verification date: 2026-10-08.

## Complete input schema


```json
{
  "type": "object",
  "properties": {
    "turbo_mode": {
      "title": "Turbo Mode",
      "type": "boolean",
      "default": false,
      "description": "Generate a video at a faster rate with a slight quality trade-off."
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "description": "The text prompt used to guide the video generation."
    },
    "image_url": {
      "title": "Image Url",
      "type": "string",
      "description": "The URL of the image used to generate the video"
    },
    "resolution": {
      "title": "Resolution",
      "enum": [
        "720p",
        "1080p"
      ],
      "type": "string",
      "default": "1080p",
      "description": "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."
    },
    "audio_url": {
      "title": "Audio Url",
      "type": "string",
      "description": "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": {
      "type": "string",
      "title": "Mask Url",
      "description": "The URL of the mask image to apply to the image. Only the person in the white area of the mask will speak."
    }
  },
  "required": [
    "image_url",
    "audio_url"
  ],
  "additionalProperties": false
}
```

## Published example

This is the provider tool’s published example. Replace example values with the user’s requested inputs, respecting the schema; do not execute an example merely to test a connection.


```json
{
  "tool_id": "fal/omnihuman-1-5",
  "input": {
    "image_url": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_image.png",
    "audio_url": "https://v3.fal.media/files/zebra/zJL_oRY8h5RWwjoK1w7tx_output.mp3",
    "resolution": "1080p"
  }
}
```

## Execute and retrieve

Inspect again before execution, explain the price and obtain the required authority. Use MCP run_tool or POST /v1/run with this tool ID, valid input and an idempotency key. Save the returned run ID and follow the actual state. If Agentik answers that the tool is temporarily unavailable, do not retry it blindly; use discovery to propose an alternative.

This tool uses deferred settlement. Follow its returned task/run instructions; preserve the existing reservation until the result is reconciled.

A partial or uncertain result can still have consumed provider resources. Consult [billing](/docs/billing.md), [idempotency](/docs/idempotency.md) and [asynchronous results](/docs/async.md).

[Provider documentation](https://fal.ai/models/fal-ai/bytedance/omnihuman/v1.5)

[REST inspection](https://api.agentik.cc/v1/tools/fal/omnihuman-1-5) · [OpenAPI](/openapi.json) · [Connection guide](/connect.md)

---

[HTML page](/providers/fal/omnihuman-1-5) · [Agent index](/llms.txt)