Introduction
Text to video on MiniMax H3 HighSpeed turns one written prompt into a 4–15 second MP4 at 768p, with its sound generated in the same pass. There is no resolution to choose, so what you decide per clip is the idea, the shape of the frame and the length.
Choose a mode by starting material
| What you have | Mode |
|---|---|
| only an idea | MiniMax H3 HighSpeed Text to video |
| a frame to animate, with an optional closing frame | MiniMax H3 HighSpeed Image to video |
| people, outfits, places, motion clips or voices | MiniMax H3 HighSpeed Reference to video |
Key features & highlights
Sound and dialogue in one pass
Each clip arrives with sound. Words in double quotes are spoken by the character you name, and ambience or music follows what you describe, so a short scene needs no audio pass afterwards.
Six aspect ratios
Pick 16:9, 9:16, 1:1, 4:3, 3:4 or 21:9 per request. The rate stays the same, so one prompt can feed a wide cut for a feed and a tall cut for Reels or Shorts.
One fixed rate
At $0.072 per second, a 6-second clip costs $0.432 and a 10-second clip $0.72. With a single resolution, you can work out the cost of a whole day's queue before it starts.
Request parameters
| Parameter | Required | Description |
|---|---|---|
prompt | Yes | Required. Accepts 1 to 7,000 characters and rejects anything longer. at least 1 characters · at most 7000 characters |
aspect_ratio | No | Frame shape: 16:9 by default, or 9:16, 1:1, 4:3, 3:4 or 21:9. It has no effect on the price. |
resolution | No |
|
duration_seconds | No | A whole number from 4 to 15 (default 5), with each second billed at the 768p rate. A 4-second request came back as a 3.75-second clip. |
Pricing
You pay for each second of the finished clip at 768p; the live rate is on the model page.
| Specification | Price |
|---|---|
| $0.072 / second |
Use cases
Daily social posts
A 9:16 clip of 5 to 8 seconds with a short line of dialogue and some ambience goes straight into a post. Keep the setting from one day to the next and change only the action and the line.
Product and ad variations
Write the same product scene with a different camera move, mood or voice line per prompt, then publish the takes that read best. Each one is a finished 768p file.
Quick turnaround for clients
When a client or a trend will not wait, a clip in roughly 22 to 35 seconds (our 4-second test clips) is quick enough to review and adjust several times in one sitting.
Prompt guide & pro tips
Write the scene in order
Say who is there, what they do first and next, where the camera sits, and add an Audio: line for sound. A clear sequence moves better than a string of adjectives; naming the light, such as golden hour or neon, sets the mood fast.
Keep dialogue short
One or two quoted lines fit a clip of 5 to 8 seconds. Name the speaker for each line, and split a longer speech across clips instead of squeezing it in.
Match length to the action
A single gesture reads well in 4 to 6 seconds; for longer clips add a second beat so the scene keeps moving. A 4-second request came back as 3.75 seconds in our test.
You pay for each second of the finished clip at 768p; the live rate is on the model page.
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${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: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "minimax/h3-highspeed/text-to-video",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"resolution": "768p",
"aspect_ratio": "16:9",
"duration_seconds": 5
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.
