Buryat Language Goes Digital in Russia
Russia has digitized and integrated the Buryat language into major digital services and education platforms.
The Buryat language is now being systematically integrated into digital services and educational platforms. It has become available in Yandex Translate, and new projects have been launched in machine translation, speech recognition, and the translation of school textbooks.
Translation From Buryat
On October 24, 2025 — Buryat Language Day — the language became available in Yandex Translate. Users can now translate texts from Buryat into more than 100 languages and back. The service is currently operating in beta mode and uses the literary standard of Buryat officially adopted in the republic.
To enable the launch, a parallel Buryat-language corpus of 120,000 sentences was transferred to Yandex in April 2025. The dataset was prepared by specialists at the state-funded Belig language center. The company later received a monolingual corpus of more than 2 million sentences. All of this data was used to train the machine-translation model.
Voice Technologies and Artificial Intelligence
In December 2025, an agreement was signed to transfer a database of Buryat-language voice recordings to Yandex. Audio data is now being collected and annotated to train speech recognition and speech synthesis models.
The data is expected to be used in voice-control systems, mobile applications, virtual assistants, and educational platforms. All materials undergo review and verification before being applied in machine-learning algorithms.
Textbooks in Buryat
In the Republic of Buryatia, work is also underway to translate school textbooks into Buryat. In 2024, authorities approved the introduction of instruction in selected subjects in Buryat for grades 1–4 at schools where it is taught as a native language.
Together, these digitization projects are laying the groundwork for broader use of the Buryat language across IT, education, and AI-powered services.
