Video-to-Audioper second
$0.00005 /second, rounded up if less than 1 second and up to a maximum of 30 seconds.
MMAudio API & Playground
MMAudio analyzes video content and creates perfectly synchronized, professional soundtracks in minutes. Use the MMAudio API to generate audio for your videos with PiAPI today!
MMAudio API Pricing
Pay-as-you-go access through PiAPI.
MMAudio API Features
Capabilities from the production model page.
Seamless Integration
Call the MMAudio AI API with a simple POST request, using standard JSON fields for model and input, and plug it into your existing backend or workflows in minutes.
Batch Processing
Process many videos in parallel by queuing multiple MMAudio tasks, ideal for content creation, video editing workflows, or any high-volume video-to-audio workloads.
Multimodal Support
Our MMAudio AI API supports text and video input modalities for effective data scaling and cross modal semantic alignment.
SOTA Performance
MMAudio achieved state-of-the-art performance amongst public models and comparable performance on Movie Gen Audio Bench
Synchronization Module
MMAudio is built with a synchronization module that aligns audio with video frames for tightly coupled, on-beat audio generation.
Multimodal Joint Training
MMAudio is trained on a wide range of audio-visual and audio-text datasets for more robust and comprehensive results across diverse content types.
Get started
Create your API key
Sign up and grab an API key from the PiAPI workspace — free credits are included on sign-up.
Top up credits
Add credits on the billing page when you are ready to scale beyond the free tier.
Call the API
POST your first task following the API docs, then poll the task until the result is ready.
Iterate in the playground
Prototype prompts and settings in the the playground above before wiring them into your product.
curl -X POST 'https://api.piapi.ai/api/v1/task' \
-H 'X-API-Key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "Qubico/mmaudio",
"task_type": "video2audio",
"input": {
"video": "YOUR_VIDEO_URL",
"prompt": "Generate background music and sound effects that match the video content.",
"negative_prompt": "",
"steps": 20,
"seed": 48511119825268
}
}'
# → { "task_id": "9d5a…", "status": "pending" }curl 'https://api.piapi.ai/api/v1/task/{task_id}' \
-H 'X-API-Key: YOUR_API_KEY'
# poll until status = completed
{
"data": {
"status": "completed",
"output": {
"audio_url": "https://img.theapi.app/ephemeral/…"
}
}
}$ npm install -g piapi-cli $ piapi run mmaudio-api \ video=YOUR_VIDEO_URL \ prompt="Generate background music and sound effects that match the video content." \ negative_prompt= \ steps=20 \ seed=48511119825268 ✓ Task completed! https://img.theapi.app/ephemeral/…
MMAudio AI API Frequently Asked Questions
What is the MMAudio AI API?
MMAudio is a framework for high-quality video-to-audio synthesis. The MMAudio AI API is a video-to-audio service available via PiAPI . It transforms silent videos into immersive audio experiences by analyzing video content and generating perfectly matched, professional soundtracks.
Where can I find the MMAudio API docs?
You can view the spec, request examples, and response format in the MMAudio API docs . Head over and generate your Audio AI with MMAudio API today!
How is MMAudio priced on PiAPI?
MM Audio API video-to-audio is billed at $0.00005 per second of video processed. You only pay for the video duration you process.
Are there refunds?
No, we do not offer refunds. When you first sign up for a PiAPI Workspace account, you receive free credits to try the MMAudio playground and API before paying.
How can I get in touch with your team?
Please email us at support@piapi.ai - we'd love to hear your feedback and explore potential collaborations!
More questions? See the API docs.