image-to-video
InfiniteTalk Fast Audio-Driven Avatar Lipsync Image-To-Video Conversational AI
InfiniteTalk fast converts one photo + audio into audio-driven talking or singing avatar videos (Image-to-Video), up to 10 minutes. Ready-to-use REST API, no coldstarts, affordable pricing.
Idle
Your request will cost $0.075 per run.
For $1 you can run this model approximately 13 times.
One more thing::
ExamplesView all
README
infinitetalk-fast
What is infinitetalk-fast?
infinitetalk-fast produces videos with precise lip sync, aligning the head, face, and body movements to the audio. It maintains identity across unlimited-length videos and also offers image-to-video generation, turning static photos into lively speaking or singing videos.
Why it looks great
-
Accurate lip synchronization: aligns lip motion precisely with audio, preserving natural rhythm and pronunciation.
-
Full-body coherence: captures head movements, facial expressions, and posture changes beyond the lips.
-
Identity preservation: maintains consistent facial identity and visual style across frames.
-
Image-to-video capability: turns static photos into realistic speaking or singing videos.
-
Instruction following: accepts text prompts to control scene, pose, or behavior while syncing to audio.
How to Use
- Upload the audio file.
- Upload the image (the person to animate).
- (Optional) Upload a mask_image to specify which regions can move.
- (Optional) Add a prompt to guide expression, style, or pose.
- Set the seed (set a fixed number for reproducibility).
- Submit the job and download the result once it's ready.
Pricing
| Metric | Value |
|---|---|
| Price per second | $0.015 |
| Minimum billed duration | 5 s |
| Minimum total price | $0.075 |
| Maximum billed duration | 600 s |
| Maximum total price per run | $9.000 |
Note
- Max clip length per job: up to 10 minutes
- Processing speed: approximately 10–30 seconds of wall time per 1 second of video (varies by resolution and queue load)
- Mask safety tip: Do not upload the full image as mask_image. The mask should only cover the regions you want to animate—otherwise the result may render as fully black.