Longcat Multi Avatar API Reference

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to meituan/longcat-multi-avatar/image-audio-to-video.

Default: meituan/longcat-multi-avatar/image-audio-to-video

stringpromptrequired

The prompt to guide the video generation.

Default: Two people are having a conversation with natural expressions and movements.

stringimagerequired

The URL of the image containing two speakers.

Optional<string>resolution

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.

Allowed values: 480p, 720p

Default: 480p

Optional<integer>num_inference_steps

The number of inference steps to use.

Range: 10 to 100

Default: 30

Optional<string>audio_url_person2

The URL of the audio file for person 2 (right side).

Default: https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/refs/heads/main/assets/avatar/multi/sing_woman.WAV

Optional<integer>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.

Range: 1 to 10

Default: 1

Optional<string>audio_url_person1

The URL of the audio file for person 1 (left side).

Default: https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/refs/heads/main/assets/avatar/multi/sing_man.WAV

Optional<string>audio_type

How to combine the two audio tracks. 'para' (parallel) plays both simultaneously, 'add' (sequential) plays person 1 first then person 2.

Allowed values: para, add

Default: para

Optional<string>bbox_person2

Bounding box for person 2. If not provided, defaults to right half of image.

Optional<number>audio_guidance_scale

The audio guidance scale. Higher values may lead to exaggerated mouth movements.

Range: 1 to 10

Default: 4

Optional<string>bbox_person1

Bounding box for person 1. If not provided, defaults to left half of image.

Optional<number>text_guidance_scale

The text guidance scale for classifier-free guidance.

Range: 1 to 10

Default: 4

Optional<integer>seed

The seed for the random number generator.

Response Schema

The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.

stringidrequired

Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.

stringstatusrequired

Current public run status.

Allowed values: pending, running, completed, failed, timeout

Optional<string>model

Public SandBase model name used for this run.

Optional<array<object>>outputs

Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.

Optional<object>error

Present only for failed or timeout runs. Contains a public error type and sanitized message.

Optional<string>error.type

Stable public error category.

Optional<string>error.message

Sanitized error message safe to show to clients.

Optional<object>usage

Usage details when available.

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: audio-to-video

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request curl -X POST https://api.sandbase.ai/v1/run \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "meituan/longcat-multi-avatar/image-audio-to-video", "prompt": "Two people are having a conversation with natural expressions and movements.", "image": "https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/refs/heads/main/assets/avatar/multi/sing.png" }' # 2. If the response is still running, poll the returned id curl https://api.sandbase.ai/v1/run/f3d2e8a1-7c4b-4a12-9d2e-123456789abc \ -H "Authorization: Bearer $SANDBASE_API_KEY"