EA1439 Yandex Speech Recognition

Etere supports Yandex Speechkit for a end-to-end connected experience, allowing broadcasters and post-producers to add speech‑to‑text directly into Etere workflows for a faster delivery within the Etere Ecosystem.

The integration supports real‑time and batch speech recognition, automatic language detection, and natural text‑to‑speech to help media businesses automate voice interactions and transcribe audio with high accuracy.

Yandex SpeechKit supported languages selection includes Russian, Kazakh, Dutch, Uzbek, English, Turkish, German, Spanish, Swedish, French, Finnish, Hebrew, Italian, Polish, and Portuguese.

Key Features
■Capture subtitles: Export and create subtitles with the selected language
■Flexible recognition modes: Creates subtitles for recorded videos and audio
■Transcribes in real-time: Suitable for live-streams
■Automatic language detection: Identifies the speaker’s language without manual configuration
■Natural speech synthesis: Converts text into speech using standard voices and customizable brand voices for consistent brand identity
■Mark vocals: Mark the stressed vowels to clarify the correct pronunciation of words
■Phonemes: Mark the correct pronunciation of words using phonemes
■Add emphasis on selected words: Emphasize essential or important words for a more dynamic speech
■Text normalization: Configure to recognise and present date and time in numerical format or convert numbers from text to digits
■Customizable speaker's speech rate: Configure the speed of the speaker's speech to suit the context
■Customizable voice pitch for the speaker: Configure the speaker's voice pitch