Model API

SadTalker

Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

Model id

Use this in every request

sadtalker/reference

This model has other modes with their own ids: sadtalker.

Run it

Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.

# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "sadtalker/reference",
  "input": {
    "source_image_url": "https://example.com/input.png",
    "driven_audio_url": "https://example.com/input.mp3",
    "reference_pose_video_url": "https://example.com/input.mp4"
  }
}'

# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"model": "sadtalker/reference", "quote_id": "QUOTE_ID", "input": {"source_image_url":"https://example.com/input.png","driven_audio_url":"https://example.com/input.mp3","reference_pose_video_url":"https://example.com/input.mp4"}}'

# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAYWAKE_API_KEY"

Input

Input fields for sadtalker/reference
Name	Type	Description
`source_image_url`required	string (image URL)	URL of the source image
`driven_audio_url`required	string (URL)	URL of the driven audio
`reference_pose_video_url`required	string (URL)	URL of the reference video
`pose_style`	integer	The style of the pose Default: `0`
`face_model_resolution`	string (enum)	The resolution of the face model Default: `256` One of: `256`, `512`
`expression_scale`	number	The scale of the expression Default: `1`
`face_enhancer`	string	The type of face enhancer to use
`still_mode`	boolean	Whether to use still mode. Fewer head motion, works with preprocess `full`. Default: `false`
`preprocess`	string (enum)	The type of preprocessing to use Default: `crop` One of: `crop`, `extcrop`, `resize`, `full`, `extfull`

Output

A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.

Job excerpt

"outputs": [
  { "type": "video", "url": "https://…", "mime_type": "video/mp4", "thumbnail_url": "https://…" }
]

Pricing

up to$1.79/ run

The exact charge for your input comes from a quote. How charges settle