meituan/longcat-single-avatar/audio-to-video
Longcat Single Avatar Audio To Video by meituan - advanced AI model for audio-to-video. Delivers high-quality results with fast inference, suitable for both creative and production workflows.
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/runmeituan/longcat-single-avatar/audio-to-videoInput Schema
8 parameters · 1 required · 7 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | The prompt to guide the video generation. · Default: "A person is talking naturally with natural expressions and movements." |
seed | integer | Optional | The seed for the random number generator. |
audio | string | Optional | The URL of the audio file to drive the avatar. |
resolution | string | Optional | Resolution of the generated video (480p or 720p). Billing is per video-second (16 frames): 480p is 1 unit per second and 720p is 4 units per second. · Options: 480p, 720p · Default: "480p" 480p720p |
num_segments | integer | Optional | Number of video segments to generate. Each segment adds ~5 seconds of video. First segment is ~5.8s, additional segments are 5s each. · Min: 1 · Max: 10 · Default: 1 |
num_inference_steps | integer | Optional | The number of inference steps to use. · Min: 10 · Max: 100 · Default: 50 |
text_guidance_scale | number | Optional | The text guidance scale for classifier-free guidance. · Min: 1 · Max: 10 · Default: 4 |
audio_guidance_scale | number | Optional | The audio guidance scale. Higher values may lead to exaggerated mouth movements. · Min: 1 · Max: 10 · Default: 4 |
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": "meituan/longcat-single-avatar/audio-to-video",
"audio": "https://static.sandbase.ai/examples/meituan/longcat-single-avatar/audio-to-video/input_audio_0.mp3",
"prompt": "A person is talking naturally with natural expressions and movements.",
"resolution": "480p",
"num_segments": 1,
"num_inference_steps": 50,
"text_guidance_scale": 4,
"audio_guidance_scale": 4
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Longcat Single Avatar
Longcat Single Avatar is a LongCat route built for audio-driven avatar animation. It turns speech audio and character controls into a synchronized talking-character video, giving creators a focused endpoint instead of forcing one generic workflow across materially different production tasks. The route belongs to a family known for efficient generation, stable visual continuity, and practical media workflows, so it is best evaluated as a creative system for intentional shots and assets rather than as a one-click novelty generator.
Use this endpoint when the input contract and deliverable match that job exactly. Its documented controls include seed (The seed for the random number generator); resolution choices (480p, 720p); num_segments (Number of video segments to generate. Each segment adds ~5 seconds of video. First segment is ~5.8s, additional segments are 5s each); num_inference_steps (The number of inference steps to use). Together, these controls help teams plan predictable iterations, compare outputs under stable settings, and connect generation to high-volume creative iteration and avatar or video production without hiding the operational choices that shape the result.
Highlights
- Purpose-built Audio-driven avatar animation. The route accepts speech audio and character controls and produces a synchronized talking-character video; its interface is scoped to that transformation, keeping source assets and creative intent explicit.
- Creative direction. Prompts can describe subject behavior, composition, camera intent, lighting, material, atmosphere, and temporal progression so the result is driven by a shot plan rather than isolated keywords.
- Route-specific control. The request exposes seed (The seed for the random number generator); resolution choices (480p, 720p); num_segments (Number of video segments to generate. Each segment adds ~5 seconds of video. First segment is ~5.8s, additional segments are 5s each); num_inference_steps (The number of inference steps to use), allowing the same concept to be tested systematically while preserving a repeatable production setup.
- Pipeline-ready output. The generated media asset is returned through the documented asynchronous output contract, which suits review queues, batch iteration, and downstream automation. Editors can review pacing, continuity, lens language, choreography, transitions, temporal artifacts, soundtrack alignment, color response, delivery framing, and cut compatibility before approval.
Pricing
| Configuration | Price |
|---|---|
| Billing rule | params.resolution == "480p" ? params.duration * 0.15 : params.duration * 0.30 |
| resolution=480p | Calculated by billing rule |
| resolution=720p | Calculated by billing rule |
When to Use
| Scenario | Why this model fits |
|---|---|
| Create the exact route output | Choose it when you need audio-driven avatar animation and already have speech audio and character controls. |
| Develop controlled variations | Keep the main brief fixed while changing one documented setting at a time to compare motion, framing, quality, or asset behavior. |
| Build repeatable batches | Use a consistent request shape for catalog, campaign, storyboard, game-asset, or social-content production. |
| Preserve source intent | Prefer this route when the supplied reference material must remain the foundation of a synchronized talking-character video. |
| Connect a media pipeline | Use asynchronous results in an automated review, approval, post-production, or asset-management workflow. |
Prompt Guide
Start with the desired result, then describe the source relationship, subject action, composition or camera behavior, lighting, style, and timing. For audio-driven avatar animation, state what must remain stable as clearly as what should change. Use only fields exposed by the schema; the example below is structurally valid for this route.
{
"prompt": "A person is talking naturally with natural expressions and movements.",
"seed": 1,
"audio": "https://static.sandbase.ai/examples/meituan/longcat-single-avatar/audio-to-video/input_audio_0.mp3",
"resolution": "480p",
"num_segments": 1
}
Technical Specs
| Specification | Value |
|---|---|
| Model ID | meituan/longcat-single-avatar/audio-to-video |
| Workflow | Audio-driven avatar animation |
| Required inputs | prompt |
seed | integer |
audio | string |
prompt | string |
resolution | string; options: 480p, 720p |
num_segments | integer; minimum: 1; maximum: 10 |
num_inference_steps | integer; minimum: 10; maximum: 100 |
text_guidance_scale | number; minimum: 1; maximum: 10 |
audio_guidance_scale | number; minimum: 1; maximum: 10 |