PixVerse V6 API

PixVerse V6 Text to video turns a written brief into a clip of 1 to 15 seconds at 360p, 540p, 720p or 1080p, in eight aspect ratios from 16:9 to 9:16 and 21:9. Describe the subject, the action and the camera; camera moves written in the prompt are followed, and PixVerse says V6 understands 20+ cinematic lens and camera controls from the prompt. Switch generate_audio on and the model generates sound with the picture. PixVerse reviews prompts and images before generating; requests it declines fail and are not charged.

Choose a PixVerse V6 mode by starting material

One paragraph, more than one framing

In our test a single paragraph about a laughing driver in a vintage teal convertible opened on a close shot of her with the scarf flying, then the camera rose to a wide aerial of the car on a cliff road above the ocean. The prompt asked for the drone to pull back and rise; the cut from close-up to aerial came from the model.

A multi-shot switch

shot_type is single by default. Set multi to let the model cut the clip into several shots. It does not change the price.

Eight aspect ratios

16:9 (default), 4:3, 1:1, 3:4, 9:16, 2:3, 3:2 and 21:9. Aspect ratio does not change the price.

Sound when you want it

generate_audio is off by default. On, the model generates ambience, effects, music and any dialogue you write in quotes. Sound on costs more per second.

Four resolutions

360p, 540p, 720p (default) and 1080p. Our test clip was 540p, 1024x576, and took about 41 seconds of model time for 5 seconds of video.

Opening and establishing shots

Write the place, the light, one camera move and the look, and you have a shot to open a scene with. Our cliff-road example does exactly that in one paragraph.

Short scenes with a spoken line

Switch audio on, describe the action and put the line in quotes. Name the ambience you want in the same prompt.

Vertical and ultrawide framing

Choose 9:16, 3:4 or 2:3 for vertical clips, or 21:9 for ultrawide. The price per second is the same for every aspect ratio.

# 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": "pixverse/v6/text-to-video",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "shot_type": "single",
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": false,
    "duration_seconds": 5
  }
}'

# 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.