SpeechKit API
Written by
Updated at April 30, 2025
You can use the SpeechKit API for speech recognition and synthesis. For API use cases, see our tutorials.
The SpeechKit API is based on the gRPC mechanism. The API methods and data structures are described using Protocol Buffers (proto 3).
The SpeechKit API does not support a resource-based approach, since it does not use Yandex Cloud resources. SpeechKit API requests are not idempotent.
Use cases
- Developing a Telegram bot for text recognition in images, audio synthesis and recognition
- Using Yandex API Gateway to set up speech synthesis in Yandex SpeechKit
- Regular recognition of audio files from Yandex Object Storage