Hedra's latest longform avatar model, audio to video will full multi-language support. Perfect for talking and singing video with speaker selection up to 10 minutes long.
Up to 10.4 MB per file
Accepts 0.5s – 600s · Up to 104.8 MB per file
Attach a start frame to place positions by clicking it.
Optional for a single speaker: one [x, y] point selects who speaks in a frame with several people. Required for multi-speaker: pass `audio` as a list and one point per audio, in the same order.
Optional. Leave it out and the video runs as long as the audio you supply. Give a value and the audio is trimmed, or padded with silence, to that length.
540p 2.5¢/second, 720p 5¢/second, 1080p 6.25¢/second.
Estimated cost: $ —
curl -X POST "https://api.hedra.com/v3/models/hedra-character-3" \ -H "Authorization: Key $HEDRA_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": { "aspect_ratio": "1:1", "resolution": "720p" }}'