ReplicateText to videoComing soon

heygen/avatar-v

Name: heygen/avatar-v
Brand: Replicate

heygen/avatar-v is a text 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: 3600s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`voice_id` required	text	—	Voice ID. Get available voice IDs from the HeyGen List All Voices API.
`avatar_id` required	text	—	Avatar ID. Must be an avatar that supports Avatar V — check `supported_api_engines` on the look via the HeyGen API.
`input_text` required	text	—	Text that the avatar will speak. Must be less than 5000 characters.
`title`	text		Title of the video.
`caption`	true or false	false	Whether to burn captions into the rendered video.
`resolution`	JSON	1080p	Output video resolution.
`voice_speed`	number 0.5 to 1.5	1	Voice speed multiplier. Value ranges from 0.5 to 1.5.
`aspect_ratio`	JSON	16:9	Output video aspect ratio.

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": "heygen/avatar-v",
    "input": {
      "voice_id": "<voice_id>",
      "avatar_id": "<avatar_id>",
      "input_text": "<input_text>"
    }
  }'