Explore All AI Models

From image generation to voice synthesis to video transcription — deAPI gives you a single, unified API to access the best open-source models.

Start for free Docs

Text-to-Image Image-to-Image Text-to-Speech Text-to-Video Image-to-Video Video-to-Text Image-to-Text Text-to-Music Text-to-Embedding Background Removal Image Upscale Audio-to-Video

Audio-to-Video

Create lip-synced talking avatars from audio and portrait images. Perfect for AI spokespersons, personalized outreach, and social media content.

LTX-2.3 22B Audio-to-Video

Up to 1024×1024 resolution. 49–241 frames at 24 fps (2–10 sec). Video synced to input audio (1–11 sec). Optional first/last frame control. Single-step distilled inference (INT8).

Sample Output

Portrait + Audio

Audio

Output

Sample Prompt


                                                    A professional young man speaking directly to the camera in a studio setting, his lips moving naturally in sync with the...
                                                    A professional young man speaking directly to the camera in a studio setting, his lips moving naturally in sync with the speech, subtle head movements and eyebrow expressions while talking, soft studio lighting, neutral grey background, shallow depth of field, corporate presentation style, smooth steady camera

Playground Coming Soon View Pricing Model Details