Speech synthesis

ADVANTAGES

Cloud | On-premise

Use it as a cloud service or deploy the software on your GPU servers
Realistic Voices

High-quality speech synthesis based on Tacotron2 and WaveNet neural network architecture
Brand Voice

We will help you create a unique voice for your branded content in any channel
High Speed

Minimal presence of pauses and delays during voiceover for a more realistic dialogue
Pronunciation Adjustment

Adjust the speed, pauses and intonation. Place the right emphasis to achieve the best sound
API

Supports REST API and gRPC. Easy integration over HTTP protocol

64-bit Linux-based operating system (CentOS version not lower than 7.X, Debian version not lower than 10.x, Astra Linux version not lower than 1.7)
docker, nvidia-docker, docker-compose
CUDA driver version 10.2+

We will promptly contact you and answer any questions