audiosarray
Up to 3 reference audio clips (voice or music).
HeyGen Video Reference to Video
heygen/heygen-video/reference-to-videoHeyGen Video Reference to Video generates a 5-15 second video guided by reference images, videos and audio.
Try the model
Playground
Input
Describe the scene, action, camera and sound.
Additional Settings More
Customize your input with more control.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each · up to 9
Up to 9 reference images (characters, products, scenes).
Up to 3 reference videos for motion or style.
Up to 3 reference audio clips (voice or music).
Output frame shape. Leave empty to follow the references (adaptive). Allowed values: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
Output resolution. 1080p and 2k cost more. Allowed values: 480p, 768p, 1080p, 2k.
515
Output length in seconds (5-15). Range: 5 to 15.
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", "images": [ "https://static.sandbase.ai/examples/dbd3acd5-a7f8-4bc6-a1c3-a6abe02c545f/input/f31c8ffc-a03e-43e6-9873-619009a711c2.png" ], "prompt": "The tiger from the reference image walks through a snowy pine forest at dusk, snowflakes falling, low-angle shot." } - Open result ↗
Input
{ "aspect_ratio": "16:9", "images": [ "https://static.sandbase.ai/examples/d1601611-1204-40e5-8c03-663e25116aad/input/050a8af9-8598-4a6b-b90c-ce437082ede7.png" ], "prompt": "The rabbit from the reference image sits by a campfire in a cozy forest clearing at night, sparks drifting upward, slow orbit shot." }
HeyGen Video Reference to Video
HeyGen Video Reference to Video generates a 5–15 second video guided by reference images, videos and audio clips.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Scene and action; describe how each reference is used. |
images | image URL[] | — | Up to 9 reference images (characters, products, scenes). |
videos | video URL[] | — | Up to 3 reference videos for motion or style. |
audios | audio URL[] | — | Up to 3 reference audio clips (voice or music). |
aspect_ratio | 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 | — | Leave empty to follow the references. |
resolution | 480p / 768p / 1080p / 2k | 768p | Output resolution; 1080p and 2k cost more. |
duration | 5–15 | 5 | Output length in seconds. |
Billing
Billed per output second: $0.07 at 480p, $0.10 at 768p, $0.18 at 1080p and 2k. References are not billed separately.
| Output | Price |
|---|---|
| 5s, 768p (default) | $0.50 |
| 5s, 480p | $0.35 |
| 10s, 1080p | $1.80 |
| Failed runs are not charged. |
Prompting
- Say which reference is the subject and which sets motion, style or sound.
Limits
- Clips are 5–15 seconds.
Also on SandBase
Other HeyGen Video endpoints: heygen/heygen-video/text-to-video, heygen/heygen-video/image-to-video.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "heygen/heygen-video/reference-to-video",
"duration": 5,
"resolution": "768p"
}
SANDBASE_JSON
)
run_id=$(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 reference images (characters, products, scenes).
promptstringrequired
Describe the scene, action, camera and sound.
videosarray
Up to 3 reference videos for motion or style.
durationinteger
Output length in seconds (5-15).
Default: 5
Minimum: 5
Maximum: 15
resolutionstring
Output resolution. 1080p and 2k cost more.
Default: "768p"
Possible values: "480p", "768p", "1080p", "2k"
aspect_ratiostring
Output frame shape. Leave empty to follow the references (adaptive).
Possible values: "21:9", "16:9", "4:3", "1:1", "3:4", "9:16"
{
"model": "heygen/heygen-video/reference-to-video",
"duration": 5,
"resolution": "768p"
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"url": "https://static.sandbase.ai/examples/dbd3acd5-a7f8-4bc6-a1c3-a6abe02c545f/output/9ecef62d-e5c5-4def-b244-64aaa8bbfc56.mp4"
}
]