New: GPT Image 2.6 is now live on KIE →
OmniHuman 1.5
omnihuman-1-5
Commercial usePart of the ByteDance API family — compare all ByteDance models →

OmniHuman 1.5 is ByteDance's AI avatar and digital human model that transforms a single image and audio into realistic talking videos with natural lip sync, facial expressions, and lifelike motion.

Model Type:
Pricing: 27 credits per second (~$0.135). High-tier top-ups (+10% bonus) bring effective pricing down to ~$0.122 per second.
Input

Click to upload or drag and drop

Supported formats: JPEG, PNG, WEBP Maximum file size: 10MB

Portrait image URL, supports any aspect ratio with subjects including people/pets/anime, etc.

Text
0 / ∞
No items yet. Click Add to start.

To have a specific subject in the image speak, use 'Subject Detection' to get the corresponding mask image and pass it as input.

Click to upload or drag and drop

Supported formats: MPEG, WAV, X-WAV, AAC, OGG, MP4 Maximum file size: 10MB

Audio URL. Duration must be < 60 seconds (recommended ≤15 seconds; exceeding this will cause degradation).

Prompt text, limited to Chinese/English/Japanese/Korean/Spanish/Indonesian, recommended ≤300 characters.

0/300

Output video resolution, default 1080.

Fast mode, sacrifices some quality to speed up generation.

Random seed. Default is -1 (random). When using the same positive integer and keeping all other parameters identical, the result will be highly consistent (with very high probability).

Output
output typevideo

README

Complete guide to using OmniHuman 1.5

ByteDance OmniHuman 1.5 API for AI Avatar and Digital Human Video Generation

Generate realistic AI avatar videos, AI lip sync video avatars, and digital human content from a single image and audio using ByteDance OmniHuman 1.5 API.

Original image

Core Capabilities of OmniHuman 1.5 API on Kie.ai

Generate AI Avatar Videos from a Single Image with OmniHuman 1.5 API

Turn a single image into a realistic AI avatar video using OmniHuman 1.5 API. Generate natural facial expressions, head movements, and lifelike animations from image and audio inputs.

Create Accurate AI Lip Sync Video Avatars with OmniHuman 1.5

Build OmniHuman 1.5 AI Lip Sync Video Avatar experiences with precise speech synchronization. Characters speak naturally with realistic mouth movements and expressive facial details.

Generate Emotion-Aware OmniHuman 1.5 Digital Human Videos

OmniHuman 1.5 Digital Human technology analyzes audio semantics and voice tone to create matching emotions, gestures, and body language for more engaging video content.

Create Full-Body AI Avatar Animations with OmniHuman-1.5 API

Unlike traditional talking photo tools, OmniHuman-1.5 API supports natural upper-body and full-body motion, helping digital humans appear more dynamic and realistic.

Integrate ByteDance OmniHuman 1.5 API into AI Video Applications

Use Bytedance OmniHuman v1.5 to power AI avatar generators, virtual influencers, digital human platforms, AI video tools, and content creation products through a scalable API.

Why Choose Kie.ai OmniHuman 1.5 API

One Portrait and One Audio Clip Under 60 Seconds

omnihuman-1-5 runs on POST /api/v1/jobs/createTask with one portrait image (people, pets or anime in any aspect ratio) and one audio clip under 60 seconds. Audio of 15 seconds or less is recommended, since longer audio degrades quality. Pricing is shown in the pricing card above.

720p or 1080p Output That Follows the Audio

The output keeps the aspect ratio of the input image, and the MP4 runs as long as the audio. 720 and 1080 are resolution tiers rather than exact heights, with 1080 as the default; the full parameter list is in the playground and API docs above.

Free Subject Detection Picks Who Speaks

omnihuman-1-5/subject-detection is free and finds up to 5 subjects in a portrait; pass the returned masks to have a specific subject speak. omnihuman-1-5/human-identification is also free and checks whether a portrait contains human, human-like or anthropomorphic subjects. New Kie.ai users receive 80 free credits for testing.

How to Use OmniHuman 1.5 API on Kie.ai

  • Step 1: Upload an Image for OmniHuman 1.5 AI Avatar Generation

    Upload a clear portrait image in JPG, PNG, or JFIF format. For best OmniHuman 1.5 API results, use a front-facing single-person image with good lighting and visible facial details.

  • Step 2: Add Audio for OmniHuman 1.5 AI Lip Sync Video Creation

    Provide speech, singing, or voice audio to drive avatar animation. OmniHuman 1.5 AI Lip Sync Video Avatar technology syncs mouth movement, expressions, and motion with audio input.

  • Step 3: Generate MP4 Video with OmniHuman 1.5 AI Video Generator

    Send request through Kie.ai API and receive MP4 video output. OmniHuman 1.5 AI Video Generator turns your image and audio into realistic digital human video for apps or workflows.

OmniHuman 1.5 API Use Cases for AI Avatar and Digital Human Applications

Create AI Influencers and Virtual Creator Videos with OmniHuman 1.5 AI Avatar

Generate realistic AI influencer content from a single image and audio file. OmniHuman 1.5 AI Avatar helps creators, agencies, and brands produce engaging short-form videos at scale.

Build AI Lip Sync Video Avatar Applications

Use OmniHuman 1.5 AI Lip Sync Video Avatar technology to power talking photo apps, avatar generators, virtual presenters, and personalized video experiences with natural speech synchronization.

Generate AI Music Videos with OmniHuman 1.5 Digital Human Technology

Transform songs, voice recordings, and audio tracks into expressive music videos. OmniHuman 1.5 Digital Human model creates realistic performances with synchronized lip movements and emotions.

Create Digital Human Spokesperson Videos for Marketing

Build brand spokespersons, product explainers, and promotional videos using ByteDance OmniHuman 1.5 API. Maintain consistent character identity across campaigns while reducing production costs.

Frequently Asked Questions

ByteDance OmniHuman 1.5 API is an AI avatar and digital human model that transforms a single image and audio input into a realistic talking video. It generates natural lip sync, facial expressions, and lifelike body movements, making it ideal for AI avatar, digital human, and AI video generation applications.

Yes. Kie.ai provides access to ByteDance OmniHuman 1.5 API through a simple developer-friendly API, making it easy to integrate AI avatar video generation into applications and workflows.

OmniHuman 1.5 AI Video Generator takes an image and an audio file as input. The model analyzes speech, emotion, and facial features to create a synchronized digital human video in MP4 format.

Yes. OmniHuman 1.5 AI Lip Sync Video Avatar technology accurately synchronizes mouth movements with speech while generating realistic facial expressions and natural character animation.

OmniHuman-1.5 API supports common image formats including JPG, JPEG, PNG, and JFIF. For best results, use a clear front-facing portrait image with a visible face.

For optimal generation quality, audio shorter than 15 seconds is recommended. Longer audio files may work, but shorter clips typically produce more stable digital human animations.

Yes. OmniHuman 1.5 Digital Human model supports realistic humans, anime characters, cartoons, and stylized avatars, allowing developers to build a wide range of creative AI video applications.

The API returns generated videos in MP4 format. This output format is widely supported across social media platforms, websites, SaaS products, and content creation workflows.

Developers use OmniHuman 1.5 API to create AI avatar generators, talking photo apps, virtual influencers, digital human platforms, AI marketing videos, educational content, and AI-powered entertainment experiences.