Vogent Voicelab is officially in public beta!
Better, faster, cheaper
Higher-quality than popular closed-source text-to-speech for a fraction of the price. Optimized compute for real-time inference and fast time-to-first-token so you can use ultra-realistic models for voice agents.
Voice clone, fine-tune, and make it your own
Use zero-shot voice cloning natively, or run our fine-tune recipes to more deeply adjust style while training and hosting on our infrastructure.
Scale up instantly
From a single voiceover to thousands of concurrent voice agents, our infrastructure scales compute with your usage and deploys across the globe.
Free
$0
/month
6 cents/1000 characters
6 cents/1000 characters
One concurrent request
One concurrent request
Starter
$20
/month
4 cents/1000 characters
4 cents/1000 characters
10 concurrent requests
10 concurrent requests
Pro
Most popular
$150
/month
3 cents/1000 characters
3 cents/1000 characters
Hosted fine-tunes
Hosted fine-tunes
Dedicated Slack channel
Dedicated Slack channel
Unlimited concurrency
Unlimited concurrency
HIPAA-compliant workspace
HIPAA-compliant workspace
Business
Contact Us
Contact Us
Dedicated account
manager
On-prem/VPC
deployments
Custom-trained voices
Custom-trained voices
Volume discounts
Volume discounts
Secure and Compliant
SOC 2 Type II and HIPAA compliant
Enterprise-level Deployment
Use our API's, or host our inference stack on-prem or in your VPC.
Committed-use Discounts
High-volume user? Get discounts by committing to monthly usage.
Use the latest voice models in seconds
Run the latest super-realistic voice models – like Sesame CSM-1B, Dia, Chatterbox, Orpheus, and more – with one API. Our hosted models run on an optimized voice inference stack and are post-trained to improve quality, so you can run state-of-the-art research in production. Get started in a few lines of code without managing compute.
nari-labs/dia
canopyai/orpheus
hexgrad/kokoro
resemble-ai/chatterbox
sesame/csm-1b
Vogent Voicelab is officially in public beta!
Use the latest voice models in seconds
Run the latest super-realistic voice models – like Sesame CSM-1B, Dia, Chatterbox, Orpheus, and more – with one API. Our hosted models run on an optimized voice inference stack and are post-trained to improve quality, so you can run state-of-the-art research in production. Get started in a few lines of code without managing compute.
hexgrad/kokoro
canopyai/orpheus
resemble-ai/chatterbox
nari-labs/dia
sesame/csm-1b
nari-labs/dia
Now in public beta!
Every voice model.
Ultra-Fast.
A fast, stable, and scalable API for top new text-to-speech models, including Sesame CSM-1B and Dia.
Connect to Content
Add layers or components to infinitely loop on your page.
Boost your productivity
A more effective way to track progress
Effortlessly turn your ideas into a fully functional, responsive, no-code SaaS website in just minutes with the set of free components for Framer.
Better, faster, cheaper
Higher-quality than popular closed-source text-to-speech for a fraction of the price. Optimized compute for real-time inference and sub-200ms time-to-first-token, so you can use ultra-realistic models for voice agents.
Voice clone, fine-tune, and make it your own
Use zero-shot voice cloning natively, or run our fine-tune recipes to more deeply adjust style while training and hosting on our infrastructure.
Everything you need
Scale up instantly
From a single voiceover to thousands of concurrent voice agents, our infrastructure scales compute with your usage and deploys across the globe.
Secure and compliant
Enhance your productivity by connecting with your favorite tools, keeping all your essentials in one place.
Enterprise-level Deployment
Use our API's, or host our inference stack on-prem or in your VPC.
Pricing
Free forever. Upgrade for unlimited tasks, better security, and exclusive features.
Free
$0
/month
6c/1000 characters
6c/1000 characters
One concurrent generation
One concurrent generation
Starter
$20
/month
4c/1000 characters
4c/1000 characters
One concurrent generation
One concurrent generation
Pro
Most popular
$150
/month
3c/1000 characters
3c/1000 characters
Hosted fine-tunes
Hosted fine-tunes
Dedicated Slack channel
Dedicated Slack channel
Unlimited concurrent generations
Unlimited concurrent generations
HIPAA-compliant workspace
HIPAA-compliant workspace
Enterprise
Contact Us
Dedicated account manager
Dedicated account manager
On-prem/VPC deployments
On-prem/VPC deployments
Custom trained voices
Custom trained voices
Volume discounts
Volume discounts
Testimonials
What our users say
Connect to Content
Add layers or components to infinitely loop on your page.
Get started in seconds
Sign up to get $5 in credits to run top voice models.
Now in public beta!
Every voice model.
Ultra-Fast.
A fast, stable, and scalable API for top new text-to-speech models, including Sesame CSM-1B and Dia.
