Skip to main content
Calibrate lets you evaluate multiple TTS providers simultaneously using your own dataset. This guide will walk you through creating an evaluation for your dataset.

​
Start a new evaluation

From the sidebar, click on Text to Speech to view all your evaluations. Click the New evaluation button to create a new evaluation.
Text to Speech Evaluations List

​
Configure settings

On the Settings tab, select the language and providers you want to compare.
Text to Speech Settings

​
Upload your dataset

Switch to the Dataset tab to add your text samples for synthesis.
Text to Speech Dataset Upload
You can also bulk upload your dataset as a CSV file with the following format: 
text
Hello, how can I help you today?
Your appointment is confirmed for tomorrow at 3 PM.
Thank you for calling. Have a great day!
Click Download sample CSV to get a template with the correct structure

​
Run evaluation

Click the Evaluate button to start the evaluation. You’ll be redirected to the results page where you can monitor progress in real-time. The Outputs tab streams the results for each text sample as it completes for each provider:
Text to Speech Outputs View

​
Leaderboard

Once all providers complete, the Leaderboard tab shows a comparison across all of them.
Text to Speech Leaderboard View

​
Next Steps

Core Concepts

Learn about the core concepts of TTS evaluation

Simulations

Run simulated conversations with your agent