How to Use Grok Imagine 1.5 Lite Text-to-Video API: Sound Included

TL;DR

• Grok Imagine 1.5 Lite Text to Video (grok-imagine-1.5-lite/text-to-video) turns one prompt into a 1–15 second video with sound built in, natively in seven aspects including vertical and square. Try it on the model page; new accounts get 200 free credits.
• Pricing is per second: 480P $0.029, 720P (default) $0.043, 1080P $0.20 — a 720p 6-second clip is $0.258.
• Everything runs on HiAPI /v1/tasks: submit for a taskId, poll, then take the video from output (temporary — save it).

What it does

• One paragraph covers picture, motion, and sound: the rig and the sound effects go into the prompt, and the clip ships with its audio track (no off switch, no surcharge).
• 1–15 seconds, any integer: duration takes whatever you pass, default 6.
• Seven aspects, natively generated: 16:9, 9:16, 1:1, 4:3, 3:2, 2:3, 3:4 — vertical and square aren't crops.
• A sibling animates stills: grok-imagine-1.5-lite/image-to-video takes one image — see the image-to-video guide.

Here's a real clip (720p · 6 s · 16:9, with wind and birdsong):

A glass hot-air balloon drifts slowly over a misty valley of terraced rice fields at sunrise. Golden light spills across the water-filled terraces, mist rolls between the hills, a flock of white egrets glides beneath the balloon. Smooth aerial tracking shot, gentle wind sounds and distant birdsong, cinematic, natural colors. No text, no logos.

grok-imagine-1.5-lite/text-to-video, 720P, 6 s, 16:9, 1280×720, sound included, $0.258. Watch the full clip →

Try this prompt →

Pricing: three tiers, per second

Tier	Per second	5 s	6 s	15 s
480P	$0.029	$0.145	$0.174	$0.435
720P (default)	$0.043	$0.215	$0.258	$0.645
1080P	$0.20	$1.00	$1.20	$3.00

HiAPI current prices, checked October 23, 2026. Note 1080P at $0.20/s is about 4.65× 720P — draft at 720p and reserve 1080P for finals. Failed tasks refund in full.

Two ways to start

Browser, 3 steps: open the model page → paste the prompt, pick duration, resolution, aspect → generate. A 720p 6-second clip is $0.258.

API, 3 steps: POST /v1/tasks to submit → take the taskId → poll to success.

curl: your first clip

curl -X POST https://api.hiapi.ai/v1/tasks \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: your-unique-key-001" \
  -d '{
  "model": "grok-imagine-1.5-lite/text-to-video",
  "input": {
    "prompt": "A glass hot-air balloon drifts slowly over a misty valley of terraced rice fields at sunrise. Golden light spills across the water-filled terraces, mist rolls between the hills, a flock of white egrets glides beneath the balloon. Smooth aerial tracking shot, gentle wind sounds and distant birdsong, cinematic, natural colors. No text, no logos.",
    "duration": 6,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }
}'

Python: submit, poll, download

import time, uuid, requests

BASE = "https://api.hiapi.ai/v1/tasks"
HEADERS = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
}

payload = {
    "model": "grok-imagine-1.5-lite/text-to-video",
    "input": {
        "prompt": "A glass hot-air balloon drifts slowly over a misty valley of terraced rice fields at sunrise. Golden light spills across the water-filled terraces, mist rolls between the hills, a flock of white egrets glides beneath the balloon. Smooth aerial tracking shot, gentle wind sounds and distant birdsong, cinematic, natural colors. No text, no logos.",
        "duration": 6,
        "resolution": "720p",
        "aspect_ratio": "16:9",
    },
}

resp = requests.post(
    BASE,
    headers={**HEADERS, "Idempotency-Key": str(uuid.uuid4())},
    json=payload,
    timeout=30,
)
resp.raise_for_status()
task_id = resp.json()["taskId"]

while True:
    task = requests.get(f"{BASE}/{task_id}", headers=HEADERS, timeout=30).json()
    print(task["status"])
    if task["status"] in ("success", "fail"):
        break
    time.sleep(5)

if task["status"] == "success":
    video = next(o for o in task["output"] if o.get("type") == "video")
    mp4 = requests.get(video["url"], timeout=120)   # temporary URL — save promptly
    with open("output.mp4", "wb") as f:
        f.write(mp4.content)
    print("saved output.mp4")

Parameters

Field	Required	Values	Notes
prompt	yes	1–4,096 chars	Picture, motion, camera, and sound in one go
duration	no	any integer 1–15, default 6	Unlike enumerated-duration models
resolution	no	480p / 720p / 1080p, default 720p	1080P at $0.20/s — watch the bill
aspect_ratio	no	7 options, default 16:9	Vertical and square are native

Any field outside the table returns a 400.

Errors you'll actually hit

Status	Meaning	What to do
400 INVALID_REQUEST	Malformed body (missing prompt, duration of 0 or 16, unknown fields)	Fix the payload against the table
402 INSUFFICIENT_QUOTA	Out of credits (no charge)	Top up and retry
429 RATE_LIMITED	Rate limited	Slow your submissions
409 / 422 IDEMPOTENCY_KEY_*	Same idempotency key resubmitted	Generate a fresh key

Terminal failures use CONTENT_POLICY_VIOLATION, TASK_FAILED, and TASK_TIMEOUT; failed tasks refund in full.

Before you ship

• Callbacks: video tasks run long — pass "callback": {"url": "https://..."} and skip polling.
• Persist outputs: the video URL in output is temporary; download immediately.
• Sound can't be disabled: strip the track in post if you need silence; the price is the same.
• 1080P in bulk adds up: $1.20 a 6-second clip; explore at 480P ($0.174) instead.

FAQ

• Yes, every clip ships with sound: describe the effects (wind, birdsong, spoken lines) and they generate with the picture; there's no off switch.
• Yes, duration is any integer 1–15, not fixed steps.
• Yes, vertical and square are native, not crops — the composition is as complete as landscape.
• Yes, $10 buys about 38 clips: $0.258 each at 720P, 6 seconds.
• Yes, all three tiers support all seven aspect ratios — resolution only affects sharpness, not which ratios are available.
• Yes, characters can speak: quote the line in the prompt (see the baker example) and dialogue arrives with the ambience.

Next: take the balloon prompt and generate your first clip; the five scenes are in the text-to-video prompt guide.