NVIDIA
Explore
Models
Blueprints
GPUs
Docs
⌘KCtrl+K
Terms of Use
Privacy Policy
Your Privacy Choices
Contact

Copyright © 2026 NVIDIA Corporation

nvidia

magpie-tts-zeroshot

Expressive and engaging text-to-speech, generated from a short audio sample.

NVIDIA NIMNVIDIA RivaTTSText-to-Speech
Apply for Access
API Reference
Accelerated by DGX Cloud

Input

Record or upload an audio file saying the following sentence:
"I consent to use my voice to create a synthetic voice." View audio sample guidelines

Record or upload a sample of your voice to set the voice style
0:00
Upload an audio file
.wav
This sentence will be generated in the audio output
0/100

Note: Your voice input will be recorded and collected to generate speech. NVIDIA will only use the voice input and generated speech to provide you with this demo experience. NVIDIA will not store the input or output and will delete them after providing the demo to you. Please do not input any confidential information or voice inputs that you do not have sufficient rights to. For more information about our data processing practices, see our Privacy Policy By clicking the run button, you consent to our collection, recording, and use of such information and the API Trial Terms of Service.

Using free API for development

GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use; and the use of this model is governed by the NVIDIA AI Foundation Models Community License.

Output

0:00