SOTA VOX TTS Speech synthesis

Voice over texts and content. Use for robots, calls and voice menus. Create your own unique voice for any task.

Learn more Request a demo

Benefits

Brand Voice- We will help you create a unique voice for voicing branded content in any channel

Cloud | On-premise

The ability to use it as a cloud service or deploy software on your own GPU servers.

Realistic voices

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

High speed

Minimum pauses and delays when voicing for a more realistic dialogue.

APIS

REST API and gRPC support. Easy HTTP/HTTPS integration

Technical specifics

Supported voices and languages

Russian language:
1. male,
2. female

‍English language:
1. male,
2. female

‍Kazakh language:
1. male,
2. female

‍Uzbek language:
1. male,
2. female

Technical requirements

1. 64-bit Linux-based operating system (CentOS 7.X or higher, Debian 10.x or higher, Astra Linux 1.7 or higher)
2. docker, nvidia-docker, docker-compose
3. cuda driver version 10.2+

Minimum hardware requirements for On-premise

- 2 CPUs (2 physical cores) with a frequency of 2.4 GhzGPU
-NVIDIA with CUDA support and at least 8 GB of RAM
- 8 GB OF RAM
- 30 GB disk space

Output format

1. 22050 Hz sampling rate
2. pcm_s16le codec
3. number of channels 1

SOTA VOX TTS Speech synthesis

Synthesize high-quality
voices for every task

Technical specifics

Supported voices and languages

Technical requirements

Minimum hardware requirements for On-premise

Output format

Try SOTA AI in action — request a demo right now!

SOTA VOX TTS Speech synthesis

Synthesize high-quality voices for every task

Technical specifics

Supported voices and languages

Technical requirements

Minimum hardware requirements for On-premise

Output format

Try SOTA AI in action — request a demo right now!

Synthesize high-quality
voices for every task