Yandex SpeechKit

Yandex SpeechKit enables app developers to use speech recognition (Speech-to-Text) and speech synthesis (Text-to-Speech) technologies.

SpeechKit is accessible via the API.

Yandex Cloud infrastructure is fully secure and in compliance with Russian Federal Law 152-FZ.

The service is subject to the Service Level Agreement. The service level is defined in the Service Level for Yandex SpeechKit.

Getting started
Convert text to speech and speech to text
Speech recognition
Find out how speech recognition works
Recognition API
Description of the recognition API v3 methods
Speech synthesis
Find out how text-to-speech conversion works
Synthesis API
Description of the synthesis API v3 methods
SpeechKit Brand Voice
Speech synthesis technology with a unique voice
SpeechKit Hybrid
Running SpeechKit voice technologies on-premise
Authentication in the API
Get an access token and use it in requests
Response format
Response headers and response codes
Quotas and limits
Technical and organizational limitations of the service
Access management
Set up access rights to work with the service
Pricing policy
Service pricing and cost calculations