Voice: speakers and sound

Seed-VC

Voice conversion without training: transfers timbre from a 1–30 second sample, can sing and work in real time; V2 also changes accent. Use only with the voice owner's consent.

Developer
Songting Liu (Plachtaa), China
First release
Sep 2024
Latest release
Apr 2025
Sizes
about 70M – 200M
License
Commercial use with conditionsGPL-3.0: commercial use possible, but modified code must be opened when distributed
Running
On your own serverNeeds a GPU
Industries
Media and production, Security
Deploy on your server Hugging Face GitHub

What it does

  • Re-voicing a video with a different voice
  • Voice anonymization in recordings
  • Real-time voice for streams

Where it is used

Media and productionEntertainment and streamingServices that need to hide a voice

Hardware requirements

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

Versions

  1. Seed-VC V2 (голос и акцент)
  2. Seed-VC v1.0 (с пением и реальным временем)
  3. Seed-VC v0.1–v0.3

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 Seed-VC be used in a commercial project?

With conditions. License: GPL-3.0: commercial use possible, but modified code must be opened when distributed. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Seed-VC need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller 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 Seed-VC support Russian?

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

Where can I download Seed-VC and what does it cost?

The Seed-VC 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

Voice: speakers and soundRVC (Retrieval-based Voice Conversion)RVC-Project community · ChinaCommercial use allowed

The most widely used open voice conversion tool: a model for a specific voice trains on 10–30 minutes of recording and works in real time. Use only with the voice owner's consent.

DetailsVoice: speakers and soundOpenVoiceMyShell and MIT · USACommercial use allowed

Instant voice cloning from a short sample with control over emotion and accent; V2 speaks several languages. Use only with the voice owner's consent.

Details

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