sandbase-ai/ai-avatar-multi
Ai Avatar Multi is sandbase-ai's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runsandbase-ai/ai-avatar-multiInput Schema
7 parameters · 2 required · 5 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
image | string | Required | URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped. |
prompt | string | Required | The text prompt to guide video generation. |
seed | integer | Optional | Random seed for reproducibility. If None, a random seed is chosen. · Min: 0 · Max: 4294967295 · Default: 81 |
resolution | string | Optional | Resolution of the video to generate. Must be either 480p or 720p. · Options: 480p, 720p · Default: "480p" 480p720p |
first_audio_url | string | Optional | The URL of the Person 1 audio file. |
second_audio_url | string | Optional | The URL of the Person 2 audio file. |
use_only_first_audio | boolean | Optional | Whether to use only the first audio file. · Default: false |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "sandbase-ai/ai-avatar-multi",
"seed": 81,
"image": "https://static.sandbase.ai/examples/bytedance/omnihuman/1.5/input_image_1.png",
"prompt": "A smiling man and woman wearing headphones sit in front of microphones, appearing to host a podcast. They are engaged in conversation, looking at each other and the camera as they speak. The scene captures a lively and collaborative podcasting session.",
"resolution": "480p",
"first_audio_url": "https://static.sandbase.ai/examples/bytedance/omnihuman/1.5/input_audio_0.mp3",
"second_audio_url": "https://static.sandbase.ai/examples/bytedance/omnihuman/1.5/input_audio_0.mp3",
"use_only_first_audio": false
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
AI Avatar Multi
AI Avatar Multi occupies the reference-led-video role in the model catalog for application builders. Its practical value is to keep a generation brief traceable from request to approval: an upstream service can confirm that it has prompt, image, submit one well-scoped job, and receive a rendered video asset for downstream approval. This positioning explains when the exact sandbase-ai/ai-avatar-multi route belongs in an architecture without borrowing promises from another version, tier, or task variant.
A useful acceptance workflow begins by checking the input readiness, acceptance criteria, and publishing destination. The caller records required values separately from optional choices such as seed, resolution, first_audio_url, second_audio_url, use_only_first_audio, runs a small representative sample, and stores the route name with the resulting artifact. Reviewers then compare that artifact with the agreed acceptance criteria, document any rejected setup, and promote only a successful request shape into larger batches. This workflow gives sandbase-ai/ai-avatar-multi measurable business context while leaving the Highlights section to explain model behavior.
Highlights
- Two-track conversation input. Separate first and second audio URLs support a pictured exchange between two participants.
- Selective first-speaker mode.
use_only_first_audiocan constrain the render to the first supplied track when a second response is not needed. - Group portrait animation. A required image anchors the appearance and placement of multiple pictured speakers during generation.
- Deterministic reruns. A seed can hold the setup steady while teams compare audio choices or dialogue timing.
Pricing
| Billing option | Price |
|---|---|
| Billing formula | params.duration * 0.2 |
| Each generated second | $0.200000 |
When to Use
| Scenario | Why it fits |
|---|---|
| Choose AI Avatar Multi | Use it when the job specifically calls for ai avatar multi and the route’s documented input contract matches assets already available in your workflow. |
| Keep the request reproducible | Use the required image, prompt explicitly, then record optional choices alongside the prompt for repeatable reruns. |
| Build controlled creative variations | Change one declared control at a time when comparing framing, format, duration, resolution, style, or other route-supported output decisions. |
| Integrate asynchronous delivery | Use this endpoint when an application can submit work, track completion, and collect the returned media URL instead of requiring an immediate inline artifact. |
| Validate before a large batch | Run representative prompts and source assets first, confirm the visual or audio behavior, then lock the successful request shape for scaled production. |
Prompt Guide
Lead with the subject or transformation, then add the composition, environment, style, lighting, motion, voice, or fidelity details relevant to this route. Keep every parameter inside the documented schema; the example below uses only fields declared for sandbase-ai/ai-avatar-multi.
{
"image": "https://static.sandbase.ai/examples/bytedance/omnihuman/1.5/input_image_1.png",
"prompt": "A smiling man and woman wearing headphones sit in front of microphones, appearing to host a podcast. They are engaged in conversation, looking at each other and the camera as they speak. The scene captures a lively and collaborative podcasting session.",
"resolution": "480p"
}
Technical Specs
| Specification | Details |
|---|---|
| Model ID | sandbase-ai/ai-avatar-multi |
| Execution mode | async |
| Task type | video |
seed | integer · optional · min 0 · max 4294967295 |
image | string · required |
prompt | string · required |
resolution | string · optional · choices: 480p, 720p |
first_audio_url | string · optional |
second_audio_url | string · optional |
use_only_first_audio | boolean · optional |