InfiniteTalk
Model Information
Display Name: InfiniteTalk
API Model ID: infinitetalk/single
Category: Audio To Video
Description: InfiniteTalk is an audio-driven talking and singing avatar video generation model that converts a single portrait photo and an audio clip into a realistic talking-head video with precise lip synchronization, up to 10 minutes long. ## Key Features - **Precise lip synchronization** — mouth movements accurately match every syllable of speech or singing - **Full-body coherence** — natural head movements, facial expressions, and body language - **Identity preservation** — consistent appearance across unlimited-length videos - **Prompt control** — text prompts to guide scene, pose, and behavior - **Long-form support** — generates videos up to 10 minutes from a single request - **Resolution options** — 480p (standard) or 720p (HD) ## Best Use Cases - AI avatars and virtual presenters for corporate training and marketing - Music video creation — animate characters singing along to tracks - Dubbing and localization — reanimate speakers with translated audio - Podcast and audiobook visualization with talking characters - Social media content with realistic talking-head videos - Educational content with animated instructors ## Parameters | Parameter | Type | Required | Default | Description | |-----------|------|----------|---------|-------------| | image | URL | Yes | — | Portrait reference image (clear, front-facing, good lighting) | | audio | URL | Yes | — | Audio file URL (up to 10 minutes) | | prompt | string | No | — | Scene control, pose, and behavior guidance | | resolution | string | No | 480p | Output resolution: 480p or 720p | | seed | integer | No | random | Seed for reproducibility | ## Pricing Cost is calculated per second of audio duration at $0.03/s (480p). A 10-second clip costs approximately $0.30, a 1-minute video costs $1.80.
How to Use This Model
To use InfiniteTalk via the HInow.ai API, use the model ID: infinitetalk/single
API Request Example
POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
{
"model": "infinitetalk/single",
"messages": [
{"role": "user", "content": "Your input here"}
]
}
Pricing
- total: $0.045
Available Parameters
- audio: Audio URL (mp3/wav, up to 10 min) to drive the talking-head animation.
- resolution: Output resolution. 720p costs 2x per second. (Options: 480p, 720p)
- mask_image: Optional mask image URL (jpg/png) marking the regions to animate.
- seed: Random seed for reproducibility. -1 (or omit) for random.
Quick Reference
To use this model, set: "model": "infinitetalk/single"
Featured: No
Documentation: https://hinow.ai/models/infinitetalk/single
API Endpoint: https://api.hinow.ai/v1
