Hedra Character 3 API

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.

Endpoint

POST https://api.hedra.com/v3/models/hedra-character-3

Example request

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": {"prompt": "a cinematic shot of a city at dusk"}}'

Parameters

num_outputsinteger

Number of outputs generated per job. Only 1 is supported.

promptstringrequired

Generation prompt.

aspect_ratiostringrequired

Output aspect ratio.

resolutionstringrequired

Output resolution.

duration_msinteger

Duration in ms. At most 600000.

start_imagerequired

Start frame (image-to-video). At most 10.4 MB.

audiorequired

Driving audio: a single reference, or a list of references for multi-speaker generation — one audio per speaker, played in list order. 1 to 4 audio files, each from 0.5s to 600s and at most 104.8 MB.

bounding_box_target

Speaker position(s) in the start frame, as normalized [x, y] image coordinates (0-1 from the top-left).