Music and soundVideo

ThinkSound / PrismAudio

Generates and edits audio for video, text or audio, first "reasoning" about the scene with a multimodal model. PrismAudio is the next version for video-to-audio.

Developer
Alibaba Tongyi (FunAudioLLM), China
First release
Jul 2025
Latest release
Mar 2026
Sizes
size not stated on the model card
License
Commercial use allowedApache 2.0 (ThinkSound), MIT (PrismAudio)
Running
On your own serverNeeds a GPU
Industries
Media and production, Marketing and content
Deploy on your server Hugging Face GitHub

What it does

  • Audio for video based on the scene
  • Editing individual sounds in a track
  • Sound effects from a description

Where it is used

Video productionAdvertisingGame development

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. PrismAudio
  2. ThinkSound

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can ThinkSound / PrismAudio be used in a commercial project?

Yes. License: Apache 2.0 (ThinkSound), MIT (PrismAudio). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does ThinkSound / PrismAudio need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does ThinkSound / PrismAudio support Russian?

Language does not matter for this model: it does not work with text.

Where can I download ThinkSound / PrismAudio and what does it cost?

The ThinkSound / PrismAudio weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Music and soundMMAudioUniversity of Illinois and Sony AI · USA / JapanNon-commercial only

Adds sound to silent video: generates noises and sound effects in sync with the on-screen action, from the video and a text prompt. One of the first strong open Foley models.

DetailsMusic and soundHunyuanVideo-FoleyTencent Hunyuan · ChinaCommercial use with conditions

Generates studio-quality (48 kHz) audio for video from the picture and a text prompt: footsteps, impacts, ambience, in sync with the action on screen.

DetailsMusic and soundStable AudioStability AI · UKCommercial use with conditions

Generates short music clips and sound effects from a description. Version 3 is split into separate models for music and for sounds.

Details

Source: github.com/FunAudioLLM/ThinkSound. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.