Yandex SpeechKit

A service that recognizes and synthesizes speech in multiple languages. SpeechKit:
The Alice voice assistant’s speech technologies adapted for use in your business solutions.

Context-based recognition
SpeechKit takes into account the probability of word combinations and lexical and stylistic features of oral speech.
Real-time synthesis
Text synthesis is done with minimum delay and works perfectly in streaming services.
Support for three languages
The service handles audio and text in three languages: Russian, English, and Turkish.
Premium voices
Premium voice speech consists of a million individual phonemes and sounds natural. Before starting speech synthesis, the service evaluates the entire text and selects the intonation characteristic of human speech.
Transparent pricing
The cost of audio recognition is automatically calculated based on the length of the track. The cost of text synthesis is based on the character count.

Implement your projects using SpeechKit

Call center automation

Automate info recognition and handling for recording customer calls. SpeechKit recognizes speech, including the last name of the caller, preferred date and time of the appointment, and other details. Let your call center staff focus on more complex issues.

Telemarketing campaigns

Give users the same information, referring to each person by name or a different ID during the call. Speech synthesis technologies help you personalize your message without involving a call center staff.

Application management

Add voice control to your app: it’s fast and convenient. Yandex SpeechKit can decode voice commands so that the app can respond to them.

Questions and answers

How do I use SpeechKit?

The service runs via the HTTP API. You can find all instructions for using the service in the documentation. Get started with the service yourself or contact us. We’ll select a partner that will develop a solution specifically for your project.

The service runs via the HTTP API. You can find all instructions for using the service in the documentation. Get started with the service yourself or contact us. We’ll select a partner that will develop a solution specifically for your project.

Why register in the Yandex.Cloud console?

To use the API, you need to get an ID (an IAM token or API key). This ID is linked to your account in the cloud.

To use the API, you need to get an ID (an IAM token or API key). This ID is linked to your account in the cloud.

What is a recognition model?

A recognition model is a neural network that is trained to recognize speech in a specific language. The models are trained on datasets generated by Yandex services and applications. This allows us to continually improve the quality of speech recognition.

A recognition model is a neural network that is trained to recognize speech in a specific language. The models are trained on datasets generated by Yandex services and applications. This allows us to continually improve the quality of speech recognition.

What audio formats does Yandex SpeechKit support for recognition?

The service can recognize audio in LPCM and OggOpus formats.

The service can recognize audio in LPCM and OggOpus formats.

Get started with Yandex SpeechKit