What is price of Dedicated GPU?

Starts with $249 per month, you can pay yearly and get 20% discount.

Is there any limit on image generation?

No, There is no limit. You can generate as many images as you want.

How much time it takes to generate images?

It takes 1.2s second to generate a image on dedicated GPU. But depends on your image size and steps.

Will i get images with my copyright?

Yes, all images you generate have your copyright. Use it as you like or sell as you like.

Support after purchase?

24X7 support team is available for any issues. Just drop message to support chat on website.

How many and what kind of models i can use?

You can upload .ckpt, lora, embeddings, controlnet and diffusers models. You can upload 100+ models.

Is there a queue for API calls?

Yes, there is a queue for API calls. If you make more than 100 API calls per second, it will be queued and processed in order. No API call will be lost.

Enterprise/Open-Source Models/Kokoro 82M

Audio

Kokoro 82M API on dedicated GPU

Kokoro 82M is a compact open TTS deployment target for teams that want private voice generation without relying on closed hosted voice APIs.

Inputs

Text, voice instructions, internal product prompts, private content

Outputs

Generated speech and controlled voice outputs

Deploy on dedicated GPU Book a deployment call

Why teams deploy Kokoro 82M

Dedicated enterprise hosting is useful for Kokoro 82M when the workload includes sensitive prompts, proprietary assets, internal product context, or runtime customization that does not belong on a shared public endpoint.

private TTS

compact voice systems

enterprise audio experimentation

Deployment profile

Modality: Audio
Deployment: Dedicated TTS runtime on enterprise GPU
Pricing floor: $1999/month

What you can run

Text to speech

Private content handling

Dedicated hosting

Enterprise storage

Common enterprise use cases

voice assistants

internal narration tools

private voice generation APIs

Source links and reference material

Official model cardhttps://huggingface.co/hexgrad/Kokoro-82M

Why ModelsLab Enterprise fits this model

Dedicated GPU deployment with no shared queue contention

100% private workloads, prompts, and generated outputs

Code access for custom runtimes, adapters, and optimization

Bring-your-own S3 storage for assets, checkpoints, and outputs

Enterprise Deployment

Deploy this model on dedicated GPU

Deploy Kokoro 82M with dedicated GPUs, private data flow, code access, and S3-backed storage so your team can run production workloads without shared infrastructure tradeoffs.

100% privacy for prompts, inputs, and outputs

Code access for custom runtimes and adapters

Bring-your-own S3 for checkpoints and generated assets

Dedicated GPU throughput with no shared queue

Pricing

$1999/month

Starting price for enterprise dedicated GPU plans. Move to higher GPU tiers when you need more VRAM, throughput, or concurrency.

CosyVoice 2 is useful for teams that want a modern open speech stack with private enterprise hosting and code-level runtime control.

Speech generationDedicated hosting

Read More Docs

Get Expert Support in Seconds

We're Here to Help.

Want to know more? You can email us anytime at support@modelslab.com

View Docs