VideoMusic and sound

Ovi

Generates video together with sound and speech from text or an image: two branches (video based on Wan 2.2 and a 5B audio branch) run in sync. Needs 24–32 GB of GPU memory.

Developer
Character.AI, USA
First release
Sep 2025
Latest release
Nov 2025
Sizes
11B
License
Commercial use allowedApache 2.0
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Media and production, Marketing and content
Deploy on your server Hugging Face GitHub

What it does

  • Short clips with talking characters
  • Animating an image with voice-over
  • Ad scene prototypes

Where it is used

Advertising and social mediaVideo productionEntertainment services

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. Ovi 1.1
  2. Ovi 1.0 (11B)

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 Ovi be used in a commercial project?

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

What hardware does Ovi 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 Ovi support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download Ovi and what does it cost?

The Ovi 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

VideoMOVAOpenMOSS / MOSI · ChinaCommercial use allowed

Generates video with sound in one pass: lip-synced speech, effects and ambience. A 32B-parameter MoE architecture, with 360p and 720p versions.

DetailsAvatarsdaVinci-MagiHumanSII-GAIR and Sand.ai · ChinaCommercial use allowed

Generates video of a talking person with sound in one go: a single transformer processes text, video and audio. Speech in 7 languages; Russian is not among them. Fast distilled versions are available.

DetailsVideoWanAlibaba · ChinaCommercial use allowed

Text-to-video and image-to-video; the small version runs on a gaming GPU. After 2.2 only applied models are open: editing (VACE), audio-driven talking characters (S2V), dancing to music (Dancer).

Details

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