Sign inGet started
ReplicateAudio to videoComing soon

bytedance/omni-human

bytedance/omni-human is an audio to video tool from Replicate that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs
In the background
Returns
video
Longest queue wait
3600s
Run deadline
1800s
Largest inline input
1024 KB
Largest input file
500 MB
Largest output
4768 MB
Outputs per run
16

Input

FieldKindDefaultDescription
audio requiredURL or file—Input audio file (MP3, WAV, etc.). For the best quality outputs audio should be no longer than 15 seconds. After 15 seconds the video quality will begin to degrade. If you have a lot of audio you want to process, we recommend splitting it into 15 second chunks.
image requiredURL or file—Input image containing a human subject, face or character.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "replicate",
    "model": "bytedance/omni-human",
    "input": {
      "audio": "<audio>",
      "image": "<image>"
    }
  }'