MiniMax H3 Max Lip Sync

MiniMax · Video · Image → Video

MiniMax H3 Max lip-synced video from a portrait and an audio track — mouth movements follow the soundtrack, optionally guided by a transcript. 5-14.8s of audio, up to 2K.

Model ID: minimax-h3-max-lip-syncWorkflow: minimax/h3-max/lip-sync/image-to-video

Lip SyncImage InputAudio Input2K5-15 sec

Try on Playground ↗

SDK API Advanced Usage Pricing

Authentication

Send your Picsart API key as a bearer token on every request.

Header

Authorization: Bearer <PICSART_API_KEY>

Make a request

One endpoint serves every model: POST to /workflows/v1/models/execute with the model id and its input in the body. The nesting is deliberate — the outer paramsis the envelope every workflow takes, and the inner one is this model's own input. Those inner names are the same unified ones the SDK takes, so a call translates one-to-one between the two — no per-vendor naming to learn.

cURL

curl -X POST 'https://api.green-salad-4efd.toolsminati.workers.dev/workflows/v1/models/execute' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "model": "minimax-h3-max-lip-sync",
    "params": {
      "startFrame": "https://cdn.example.com/input.jpg",
      "audioUrl": "https://cdn.example.com/input.mp3",
      "resolution": "768p"
    }
  }
}'

Async (submit & poll)

This model can run longer than the sync limit (~20s), so send it to /workflows/v1/models/submit, which returns a task id, and poll /workflows/v1/models/{taskId}/result until response.status is COMPLETED or FAILED.

cURL

# 1. Submit the job
curl -X POST 'https://api.green-salad-4efd.toolsminati.workers.dev/workflows/v1/models/submit' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "model": "minimax-h3-max-lip-sync",
    "params": {
      "startFrame": "https://cdn.example.com/input.jpg",
      "audioUrl": "https://cdn.example.com/input.mp3",
      "resolution": "768p"
    }
  }
}'
# → { "status": "success", "response": { "id": "task_abc123" } }

# 2. Poll until response.status is COMPLETED
curl 'https://api.green-salad-4efd.toolsminati.workers.dev/workflows/v1/models/task_abc123/result' \
  -H 'Authorization: Bearer $PICSART_API_KEY'

Result body

{
  "status": "success",
  "response": {
    "id": "task_abc123",
    "status": "COMPLETED",
    "result": {
      "url": "https://cdn.green-salad-4efd.toolsminati.workers.dev/…/result",
      "items": [
        {
          "url": "https://cdn.green-salad-4efd.toolsminati.workers.dev/…/result"
        }
      ],
      "model": "minimax-h3-max-lip-sync"
    },
    "usage": {
      "credits": 1
    }
  }
}

Parameters

6 parameters, sent inside the inner paramsobject. Identical to the SDK's — one parameter set, whichever transport you use.

Parameter	Type	Required	Default	Details
`startFrame` Portrait Image	`file (image)`	yes	`—`	—
`audioUrl` Audio Track	`file (audio)`	yes	`—`	—
`resolution`	`enum`	no	`768p`	480p, 768p, 1080p, 2k
`enableTranscription` Transcription	`boolean`	no	`false`	—
`seed`	`range`	no	`-1`	-1–2147483647
`enableSafetyChecker` Safety Checker	`boolean`	no	`true`	—

Response

The body arrives in the gateway's status envelope, so the output is at response.result — alongside the task id, its status and the credits charged. Asset models return url plus an items array; text models return text instead.

Response body

{
  "status": "success",
  "response": {
    "id": "task_abc123",
    "status": "COMPLETED",
    "result": {
      "url": "https://cdn.green-salad-4efd.toolsminati.workers.dev/…/result",
      "items": [
        {
          "url": "https://cdn.green-salad-4efd.toolsminati.workers.dev/…/result"
        }
      ],
      "model": "minimax-h3-max-lip-sync"
    },
    "usage": {
      "credits": 1
    }
  }
}