Qubico Logo

Documentation

API Documentation

Qubico/mmaudio API Reference

Complete API documentation for the MMAudio model supporting video-to-audio generation, creating synchronized audio from video content.

Quick Start
Get started with MMAudio model in minutes

Base URL

https://api.qubico.ai/v1/inference

Header Params

x-api-key: YOUR_API_KEY

Model ID

Qubico/mmaudio
Video-to-Audio Generation
Generate synchronized audio from video content

Request Example

POST https://api.qubico.ai/v1/inference
Content-Type: application/json
x-api-key: YOUR_API_KEY

{
  "model": "Qubico/mmaudio",
  "input": {
    "video": "https://example.com/input-video.mp4",
    "prompt": "Natural outdoor sounds with birds chirping",
    "negative_prompt": "music, speech, artificial sounds",
    "steps": 25,
    "seeds": 48511119825268
  },
  "config": {
    "webhook_config": {
      "endpoint": "https://your-webhook.com/callback",
      "secret": "your_webhook_secret"
    }
  }
}

Response Example

{
  "task_id": "task_12345678",
  "status": "pending",
  "model": "Qubico/mmaudio",
  "created_at": "2024-01-15T10:30:00Z",
  "estimated_time": 45
}
Parameters Reference
Complete list of available parameters for MMAudio model

Required Parameters

model
string
required

Model identifier. Must be "Qubico/mmaudio"

input.prompt
string
required

Prompt text for audio generation. Maximum 500 characters.

input.video
string
required

Base64 or URL of the input video (mp4 only). Maximum duration: 60 seconds.

Optional Parameters

input.negative_prompt
string
optional

Negative prompt text for audio generation. Maximum 200 characters.

input.steps
integer
optional

Number of steps for audio generation. Range: 20-50, Default: 25

input.seeds
integer
optional

Random seed for reproducible results. Usually random and could be selected optional (e.g., 48511119825268)

Configuration Parameters

config.webhook_config
object
optional

Webhook configuration for async notifications

endpoint - Webhook URL
secret - Webhook secret for verification
Response Format
Understanding API responses and status codes

Initial Response (202 Accepted)

{
  "task_id": "task_12345678",
  "status": "pending",
  "model": "Qubico/mmaudio",
  "created_at": "2024-01-15T10:30:00Z",
  "estimated_time": 45
}

Completed Response (GET /v1/tasks/task_id)

{
  "task_id": "task_12345678",
  "status": "completed",
  "model": "Qubico/mmaudio",
  "created_at": "2024-01-15T10:30:00Z",
  "completed_at": "2024-01-15T10:31:15Z",
  "results": [
    {
      "url": "https://cdn.qubico.ai/results/audio_1.wav",
      "duration": 10.0,
      "format": "wav",
      "sample_rate": 16000,
      "channels": 1
    }
  ],
  "usage": {
    "credits_used": 1,
    "processing_time": 75.2
  }
}

Status Values

pending
Task is queued
processing
Task is being processed
completed
Task completed successfully
failed
Task failed with error
Error Handling
Common error codes and how to handle them

Error Response Format

{
  "error": {
    "code": "INVALID_VIDEO_FORMAT",
    "message": "Video format not supported. Please use MP4, AVI, or MOV format.",
    "details": {
      "provided_format": "webm",
      "supported_formats": ["mp4", "avi", "mov"]
    }
  }
}
Code Examples
Ready-to-use code snippets in popular languages
curl -X POST https://api.qubico.ai/v1/inference \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "model": "Qubico/mmaudio",
    "input": {
      "video": "https://example.com/input-video.mp4",
      "prompt": "Natural outdoor sounds with birds chirping",
      "negative_prompt": "music, speech, artificial sounds",
      "steps": 25,
      "seeds": 48511119825268
    },
    "config": {
      "webhook_config": {
        "endpoint": "https://your-webhook.com/callback",
        "secret": "your_webhook_secret"
      }
    }
  }'
Rate Limits & Pricing
Usage limits and cost information

Rate Limits

Requests per minute:
20
Concurrent tasks:
5
Daily requests:
500

Pricing

Video-to-Audio:
$0.05/second
Free trial credits:
200 seconds