Talking avatar (OmniHuman) API
1 endpoint on fal.ai, paid per call at the provider's price.
Versions
Inputs
- Image URL
- The URL of the image used to generate the video
- Audio URL
- The URL of the audio file to generate the video
- Turbo mode
- Generate a video at a faster rate with a slight quality trade-off. Optional
- Prompt
- The text prompt used to guide the video generation. Optional
- Resolution
- The resolution of the generated video (720p or 1080p). Optional
- Mask URL
- The URL of the mask image to apply to the image. Optional
Other video generation models
- Seedance7 toolsUsage based
- Kling6 tools$0.112/s
- Veo 3.14 toolsUsage based
- Gemini Omni3 toolsUsage based
- MiniMax Hailuo20 tools$0.002/s
- Wan1 toolUsage based
- LTX2 toolsUsage based
- Luma Ray2 tools$0.03/s
- PixVerse2 toolsUsage based
- Grok Imagine Video5 toolsUsage based
- Vidu2 toolsUsage based
- Lip sync5 tools$0.07/unit
Questions
Which Talking avatar (OmniHuman) versions can my agent run?
OmniHuman 1.5 talking avatar from image and audio.
How is it billed?
At the cost the provider reports for each call, with no markup. Your agent sees the maximum before it runs a tool.
Connect your agent to 2,400+ tools for free
Sign in with Google or GitHub. No card required.