Model API

P-Video 2 Pro Avatar

Turn one portrait and a speech recording or a typed script into a lip-synced talking video. The video runs as long as the speech, from 1 second to 3 minutes, at 480p or 768p and 24 fps. Priced per second of speech.

Model id

Use this in every request

p-video-2-pro-avatar

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": "p-video-2-pro-avatar",
  "input": {
    "inputImage": [
      "https://example.com/input.png"
    ],
    "prompt": "A red ceramic cup on a wooden table, soft morning light"
  }
}'

# 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": "p-video-2-pro-avatar", "quote_id": "QUOTE_ID", "input": {"inputImage":["https://example.com/input.png"],"prompt":"A red ceramic cup on a wooden table, soft morning light"}}'

# 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 p-video-2-pro-avatar
Name	Type	Description
`inputImage`required	array of image URLs	Required. One clear portrait used as the first frame. JPG, PNG or WebP, up to 20 MB. It sets the aspect ratio of the video.
`script`	string	Use a script or a speech recording. The exact words the avatar speaks, up to about 3 minutes of speech. The longest likely reading is held and you pay for the actual length.
`inputAudio`	array of image URLs	Use a speech recording or a script. The speech the avatar lip-syncs to, 1 second to 3 minutes, MP3 or WAV. The video matches its length and the price follows it. Used instead of the script. Default: `[]`
`voice`	string (enum)	Voice that reads the script. Not used with a speech recording. Default: `Zephyr (Female)`
`voiceLanguage`	string (enum)	Language of the script. Not used with a speech recording. Default: `English (US)` One of: `English (US)`, `English (UK)`, `Spanish`, `French`, `German`, `Italian`, `Portuguese (Brazil)`, `Japanese`, `Korean`, `Hindi`
`voicePrompt`	string	Optional. Tone, pacing, accent and emotion for the script. Not spoken. Not used with a speech recording.
`prompt`	string	Optional. Describe what the video should show. Defaults to "The person is talking."
`resolution`	string (enum)	Required. Output resolution. The video is always 24 fps. Default: `768p` One of: `480p`, `768p`
`promptUpsampling`	string (enum)	Optional. Adds the scene's own motion from the portrait (rain, lights, background, body movement) after your prompt. Off uses the prompt exactly. Default: `true` One of: `true`, `false`
`seed`	string	Optional. Random seed. Leave empty for a new result each time; set it to repeat one.

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

480p$0.04/ second
768p$0.07/ second

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