audiosarray
Up to 3 reference audio URLs (2-15 seconds each, at most 15 seconds combined), referenced in the prompt as Audio 1, Audio 2, and so on. Audio requires at least one reference image or video.
MiniMax H3 Max Reference to Video
minimax/h3-max/reference-to-videoMiniMax H3 Max by MiniMax generates a 5-15 second video with native audio at 480P or 768P that keeps subjects, motion, and voice consistent with reference images, videos, and audio.
Try the model
Playground
Input
Text prompt for video generation. Refer to reference assets by their modality and order in the reference lists: Image 1, Image 2, Video 1, Audio 1, and so on.
Additional Settings More
Customize your input with more control.
Output aspect ratio. Omit to let the model choose from the prompt and reference inputs. Allowed values: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
The native generation resolution of the video. Allowed values: 480P, 768P.
515
The duration of the video in seconds. Range: 5 to 15.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each · up to 9
Up to 9 subject or style reference image URLs, referenced in the prompt as Image 1, Image 2, and so on.
How much effort to spend rewriting the prompt before generation. `balanced` returns in about a second; `quality` spends up to ~30 seconds on a richer prompt. Allowed values: balanced, quality.
Up to 3 motion or reference video URLs (2-15 seconds each, at most 15 seconds combined), referenced in the prompt as Video 1, Video 2, and so on.
Up to 3 reference audio URLs (2-15 seconds each, at most 15 seconds combined), referenced in the prompt as Audio 1, Audio 2, and so on. Audio requires at least one reference image or video.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "aspect_ratio": "16:9", "audios": [ "https://static.sandbase.ai/examples/c1934625-e6b2-40d7-bf17-9017e8ca6191/input/233a82cc-7618-4314-967c-b14207086234.mp3" ], "duration": 9, "images": [ "https://static.sandbase.ai/examples/c1934625-e6b2-40d7-bf17-9017e8ca6191/input/26f1c4a1-bfb2-4db6-a27f-aafabd36b0d5.png" ], "prompt": "Image 1 is the male character. Audio1 is him talking. Lipsync Image1 to Audio1", "prompt_expansion_mode": "balanced", "resolution": "480P" } - Open result ↗
Input
{ "aspect_ratio": "16:9", "audios": [ "https://static.sandbase.ai/examples/ef24fea0-6082-44fd-99c7-ded480031255/input/4665aac1-b08b-4f94-b5de-87db68959484.mp3" ], "duration": 5, "images": [ "https://static.sandbase.ai/examples/ef24fea0-6082-44fd-99c7-ded480031255/input/93ac1b42-6ede-4871-a42c-82e90164a227.png" ], "prompt": "Image 1 is the male character. Audio1 is him talking. Lipsync Image1 to Audio1", "prompt_expansion_mode": "balanced", "resolution": "480P" }
MiniMax H3 Max Reference to Video
MiniMax H3 Max reference-to-video: images, videos, and audio references keep subjects, motion, and voice consistent in a 5–15 second clip.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 50,000 characters. |
aspect_ratio | 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 | — | Output frame shape. |
resolution | 480P / 768P | 768P | Sets the per-second rate. |
duration | integer 5–15 | 5 | Output length in seconds. |
images | image URL[] (≤9) | — | Reference images, Image 1, Image 2, … |
prompt_expansion_mode | balanced / quality | balanced | balanced rewrites the prompt lightly; quality expands it more for richer detail. |
videos | video URL[] (≤3) | — | Reference clips, Video 1, … |
audios | audio URL[] (≤3) | — | Reference audio, Audio 1, … |
Billing
You pay for output seconds: $0.08 at 768P and $0.05 at 480P. Very large reference sets (over 4,096 reference tokens) add $0.02 per 1,000 extra tokens.
| Output | 768P | 480P |
|---|---|---|
| 5s (default) | $0.40 | $0.25 |
| 10s | $0.80 | $0.50 |
| 15s | $1.20 | $0.75 |
Failed runs are not charged.
Prompting
- Describe subject, action, camera, and sound in order.
- Quote dialogue and name the speaker.
Limits
- Clips are 5–15 seconds.
Also on SandBase
Other MiniMax H3 Max endpoints: minimax/h3-max/text-to-video, minimax/h3-max/image-to-video, minimax/h3/reference-to-video (2K).
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "minimax/h3-max/reference-to-video",
"images": [
"https://static.sandbase.ai/examples/minimax/mirrored/example_inputs/hailuo23/pro_i2v_in.jpg"
],
"prompt": "Image 1 is the female protagonist. Image 2 is her small dog. Keep the woman and dog consistent with their respective reference images while they walk together through a sunlit garden.",
"duration": 5,
"resolution": "768P",
"prompt_expansion_mode": "balanced"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
imagesarray
Up to 9 subject or style reference image URLs, referenced in the prompt as Image 1, Image 2, and so on.
promptstringrequired
Text prompt for video generation. Refer to reference assets by their modality and order in the reference lists: Image 1, Image 2, Video 1, Audio 1, and so on.
videosarray
Up to 3 motion or reference video URLs (2-15 seconds each, at most 15 seconds combined), referenced in the prompt as Video 1, Video 2, and so on.
durationinteger
The duration of the video in seconds.
Default: 5
Minimum: 5
Maximum: 15
resolutionstring
The native generation resolution of the video.
Default: "768P"
Possible values: "480P", "768P"
aspect_ratiostring
Output aspect ratio. Omit to let the model choose from the prompt and reference inputs.
Possible values: "21:9", "16:9", "4:3", "1:1", "3:4", "9:16"
prompt_expansion_modestring
How much effort to spend rewriting the prompt before generation. `balanced` returns in about a second; `quality` spends up to ~30 seconds on a richer prompt.
Default: "balanced"
Possible values: "balanced", "quality"
{
"model": "minimax/h3-max/reference-to-video",
"images": [
"https://static.sandbase.ai/examples/minimax/mirrored/example_inputs/hailuo23/pro_i2v_in.jpg"
],
"prompt": "Image 1 is the female protagonist. Image 2 is her small dog. Keep the woman and dog consistent with their respective reference images while they walk together through a sunlit garden.",
"duration": 5,
"resolution": "768P",
"prompt_expansion_mode": "balanced"
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"poster": "https://static.sandbase.ai/examples/posters/bfca29c8271a0d41b3ae.jpg",
"source": "Completed user prediction (human visual safety screened)",
"source_url": "https://www.sandbase.ai",
"url": "https://static.sandbase.ai/examples/c1934625-e6b2-40d7-bf17-9017e8ca6191/output/47cc4d11-7757-4ca2-84b0-90ed513f8158.mp4"
}
]