Generate Audio

Developing

POST

https://api.piapi.ai/api/v1/task

mmaudio

This endpoint from PiAPI's mmaudio API can generate audio based on video. Users could upload their video then use our mmaudio API to generate sound of the video based on the prompt provided by users.

Model	Price (USD)
Qubico/mmaudio	$0.0005/second, rounded up if less than 1 second and up to a maximum of 30 seconds.

Request

Header Params

x-api-key

string

optional

your api key

Body Params application/json

model

enum<string>

required

Model name, currently select Qubico/mmaduio.

Allowed value:

Qubico/mmaudio

task_type

enum<string>

required

Currenly could choose video2audio.

Allowed value:

video2audio

input

object

required

prompt

string

required

Prompt text for audio generation.

negative_prompt

string

optional

Negative prompt text for audio generation

video

string

required

Base64 or URL of the input video (mp4 only).

steps

integer

optional

Number of steps for audio generation (varies from 20 to 50).

seeds

integer

optional

Usually random and could be selected optional (e.g., 48511119825268).

config

object

required

webhook_config

object

optional

Example

{
  "model": "Qubico/mmaudio",
  "task_type": "video2audio",
  "input": {
    "prompt": "",
    "negative_prompt": "",
    "video": "",
    "steps": 20,
    "seed": 48511119825268
  },
  "config": {
    "webhook_config": {
      "endpoint": "",
      "secret": ""
    }
  }
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.piapi.ai/api/v1/task' \
--header 'x-api-key;' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "Qubico/mmaudio",
    "task_type": "video2audio",
    "input": {
        "prompt": "",
        "negative_prompt": "",
        "video": "",
        "steps": 20,
        "seed": 48511119825268
    },
    "config": {
        "webhook_config": {
            "endpoint": "",
            "secret": ""
        }
    }
}'

Responses

🟢200Success

application/json

Body

model

string

optional

task_type

string

optional

input

object

optional

prompt

string

required

negative_prompt

string

optional

video

string

required

steps

integer

optional

seed

integer

optional

config

object

optional

webhook_config

object

optional

Example

{
  "model": "Qubico/mmaudio",
  "task_type": "video2audio",
  "input": {
    "prompt": "",
    "negative_prompt": "",
    "video": "",
    "steps": 20,
    "seed": 48511119825268
  },
  "config": {
    "webhook_config": {
      "endpoint": "",
      "secret": ""
    }
  }
}

Modified at 2025-04-01 08:49:53

Get Task

Generate Audio