Video Image to Video fal.ai

OmniHuman 1.5 Avatar

OmniHuman 1.5 Avatar costs $0.960/clip on FairStack — a image to video model for Talking-head video, Avatar presenters, Lipsync content. No subscription required. Pay per generation with full REST API access. FairStack applies a transparent 20% margin on infrastructure cost so you always see the real price.

FairStack price

$0.960/clip

Try OmniHuman 1.5 Avatar API Quickstart Last updated 2026-06-27

What is OmniHuman 1.5 Avatar?

Key Features

Audio-driven avatar

Emotion-correlated motion

720p/1080p

What are OmniHuman 1.5 Avatar's strengths?

Best open avatar quality

Expressive lipsync

Affordable

What are OmniHuman 1.5 Avatar's limitations?

Requires an audio track

Single-person focus

What is OmniHuman 1.5 Avatar best for?

Talking-head video Avatar presenters Lipsync content

How much does OmniHuman 1.5 Avatar cost?

Metric

FairStack

Details

Price per generation

$0.960

Includes 20% margin

Per-second rate

$0.1600/sec

Billed per second of output

Subscription

None

Pay per generation only

How does OmniHuman 1.5 Avatar perform across capabilities?

OmniHuman 1.5 — avatar lane anchor

motion quality

86%

visual quality

85%

lipsync accuracy

88%

temporal coherence

85%

character consistency

87%

How do I use the OmniHuman 1.5 Avatar API?

curl

curl -X POST https://api.fairstack.ai/v1/generations/video \
  -H "Authorization: Bearer $FAIRSTACK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "omnihuman-1-5-i2v",
    "prompt": "Your prompt here"
  }'

Python

import requests

response = requests.post(
    "https://api.fairstack.ai/v1/generations/video",
    headers={
        "Authorization": f"Bearer {FAIRSTACK_API_KEY}",
        "Content-Type": "application/json",
    },
    json={
        "model": "omnihuman-1-5-i2v",
        "prompt": "Your prompt here",
    },
)

result = response.json()
print(result["url"])

Node.js

const response = await fetch(
  "https://api.fairstack.ai/v1/generations/video",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.FAIRSTACK_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      model: "omnihuman-1-5-i2v",
      prompt: "Your prompt here",
    }),
  }
);

const result = await response.json();
console.log(result.url);

What parameters does OmniHuman 1.5 Avatar support?

Parameter

Type

Default

Details

image_url

string

—

audio_url

string

—

prompt

string (optional)

—

resolution

enum

1080p

Options: 720p, 1080p

turbo_mode

boolean (optional)

—

Frequently Asked Questions

How much does OmniHuman 1.5 Avatar cost?

OmniHuman 1.5 Avatar costs $0.960/clip on FairStack as of 2026-06-27. This price includes FairStack's transparent 20% margin on infrastructure cost. No subscription or monthly fee — you pay per generation only. Minimum deposit is $1.

What is OmniHuman 1.5 Avatar and what is it best for?

OmniHuman 1.5 is ByteDance's best open audio-driven avatar model and the anchor of FairStack's lipsync/avatar lane. Give it a photo of a person plus an audio track and it synthesizes an expressive talking-head video where the character's emotions and movements correlate with the audio. 720p (to 60s) or 1080p (to 30s), optional prompt + mask + turbo mode. $0.16/s. OmniHuman 1.5 Avatar is best for Talking-head video, Avatar presenters, Lipsync content. Available via FairStack's REST API with curl, Python, and Node.js SDKs.

Does OmniHuman 1.5 Avatar have an API?

Yes. OmniHuman 1.5 Avatar is available via FairStack's REST API at api.fairstack.ai. Send a POST request to /v1/generations/video with your API key and prompt. Works with curl, Python requests, Node.js fetch, and any HTTP client. No SDK installation required.

How does OmniHuman 1.5 Avatar compare to other video models?

OmniHuman 1.5 Avatar excels at Talking-head video, Avatar presenters, Lipsync content. It is a image to video model priced at $0.960/clip on FairStack. Key strengths: Best open avatar quality, Expressive lipsync. Compare all video models at fairstack.ai/models.