audiostringrequired
Speech or song that drives the performance. WAV or MP3, 4-300 seconds, up to 15 MB.
ByteDance OmniHuman 2.0
bytedance/omnihuman/2.0OmniHuman 2.0 by ByteDance turns a single image and an audio track into a talking or performing video that follows the audio.
Try the model
Playground
Input
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Person or character to animate. 300-6000 px per side, aspect ratio 0.4-2.5, up to 30 MB.
This field is required.
Speech or song that drives the performance. WAV or MP3, 4-300 seconds, up to 15 MB.
Optional direction for scene, gestures and camera.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "audio": "https://static.sandbase.ai/examples/4e4bda6c-b42a-40d2-8777-ec0c9dc7ca6b/input/8f429735-ac39-48b6-aa3c-360f822d11fa.mp3", "image": "https://static.sandbase.ai/examples/4e4bda6c-b42a-40d2-8777-ec0c9dc7ca6b/input/117a23db-2541-4338-a76a-11206be9e9e7.png", "prompt": "She speaks warmly to the camera with natural hand gestures." } - Open result ↗
Input
{ "audio": "https://static.sandbase.ai/examples/4b4402b0-ac66-4de9-89d0-c6dadd102228/input/2280d23d-3ccc-4b1f-a855-c799ca34804a.mp3", "image": "https://static.sandbase.ai/examples/4b4402b0-ac66-4de9-89d0-c6dadd102228/input/d3699201-5618-49d9-91d0-d7a8f340865f.png", "prompt": "He speaks confidently to the camera in Times Square at night, small natural head movements." }
ByteDance OmniHuman 2.0
OmniHuman 2.0 turns a single image and an audio track into a talking or performing video, with lip sync, gestures and expressions that follow the audio.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
image | image URL, required | — | Person or character to animate. 300–6000 px per side, aspect ratio 0.4–2.5, up to 30 MB. |
audio | audio URL, required | — | Speech or song, WAV or MP3, 4–300 seconds, up to 15 MB. |
prompt | string | — | Optional direction for scene, gestures and camera. |
Billing
$0.105 per output second; the output is as long as the audio. The quote before submission assumes 5 seconds when the audio length cannot be read.
| Audio | Price |
|---|---|
| 5s audio | $0.525 |
| 30s audio | $3.15 |
| 60s audio | $6.30 |
| Failed runs are not charged. |
Prompting
- Describe gestures and camera; the lips follow the audio automatically.
Limits
- Audio must be 4–300 seconds.
Also on SandBase
Previous version: bytedance/omnihuman/1.5.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "bytedance/omnihuman/2.0",
"audio": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_audio.mp3",
"image": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_image.png"
}
SANDBASE_JSON
)
run_id=$(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
imagestringrequired
Person or character to animate. 300-6000 px per side, aspect ratio 0.4-2.5, up to 30 MB.
promptstring
Optional direction for scene, gestures and camera.
{
"model": "bytedance/omnihuman/2.0",
"audio": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_audio.mp3",
"image": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_image.png"
}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/4e4bda6c-b42a-40d2-8777-ec0c9dc7ca6b/output/678ef1e5-25c7-4172-bccd-e5456509e237.mp4"
}
]