Think Sound

Think Sound

Playground

Upload a video and provide a text description to generate realistic audio.

Features

ThinkSound

What is ThinkSound?

ThinkSound is a cutting-edge video-to-audio generation model. By leveraging advanced deep learning techniques, this model can generate high-quality, realistic audio that aligns perfectly with the content of the input video.

Key Features:

• Video-to-Audio Generation: Converts video content into corresponding audio tracks, enhancing the overall multimedia experience.
• High-Quality Output: Produces clear and realistic audio that matches the context and actions depicted in the video.

Tips

For optimal results, ensure that the input video has clear visuals and distinct actions or events that can be translated into audio.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/think-sound" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "video": "",
    "prompt": "",
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"