{ "task_id": "d9oo2z1s89lobg8oz5", "user_id": 1, "version": "11fee5368eda61d569f53f1b24ce1c53b06c867157cd833e9a0a97b66096f974", "error": null, "total_time": 37, "predict_time": 37, "logs": null, "output": [ "https://vmodel.ai/data/model/vmodel/talking-photo-turbo/result.mp4" ], "status": "succeeded", "create_at": 1746492954, "completed_at": 1746493015, "input": { "avatar": "https://vmodel.ai/data/model/vmodel/talking-photo-turbo/demo.png", "speech": "https://vmodel.ai/data/model/vmodel/talking-photo-turbo/examples_wav_talk_male_law_10s.wav" } }
The Talking Photo API brings static portraits to life by combining a photo and an audio input to generate realistic talking avatar videos. Ideal for virtual assistants, content creation, interactive entertainment, and personalized video messaging.
The Talking Photo API creates a facially animated video from a user-provided photo and an audio file. It delivers natural lip-sync and facial expressions with high visual quality and fast response, suitable for both real-time and batch use cases.
Image Input Formats:
Audio Input Formats:
Output Format:
All API requests require a valid API token, which is available after account registration.
Send a POST request with an image and audio file. For complete parameter documentation and example code, refer to the developer documentation.
For technical support or business inquiries: š§ [email protected]