Introduction
VEED Fabric 1.0 is VEED's image-to-talking-video model. Pass a portrait in image_url and a speech recording in audio_url, choose resolution, and it returns the same face speaking those words.
Key features & highlights
Works on more than photos
Photos, oil paintings, anime frames and mascots all animate. In our painting test the brush texture survived while the mouth moved.
Audio sets the length and the rhythm
The clip is exactly as long as the audio, up to five minutes. Pauses in the recording become pauses on screen.
The frame keeps your picture's shape
A portrait image gives a portrait video. 720p gave 832×1088 for a 3:4 painting; 480p gave 512×768 for a 2:3 photo.
Request parameters
| Parameter | Required | Description |
|---|---|---|
image_url | Yes | Required. JPEG, PNG or WebP with one clearly visible face. at least 1 characters |
audio_url | Yes | Required. Speech in MP3, WAV or another common format, up to five minutes. at least 1 characters |
resolution | No | 480p or 720p. 720p costs more per second; both keep the aspect ratio of the image. |
Pricing
Billed per second of the audio, rounded up to a whole second, at the rate of the chosen resolution. The image is free. Failed renders are not charged.
| Specification | Price |
|---|---|
| $0.096 / second |
| $0.18 / second |
Use cases
Mascots and virtual hosts
Give a brand character a voice for onboarding clips or product updates.
Narrated stills
Let a historical portrait or a poster figure deliver a line for an exhibition or an ad.
Prompt guide & pro tips
Face the camera
A frontal or three-quarter face that fills part of the frame gives the cleanest lip shapes.
Clean speech
Use one voice without music. If the recording is noisy, clean it before you send it.
Draft at 480p
Check timing on the cheaper tier, then render the final version at 720p.
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SPICY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "veed/fabric-1.0/talking-avatar",
"input": {
"audio_url": "https://example.com/reference.mp3",
"image_url": "https://example.com/reference.png",
"resolution": "480p"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.




