Yandex Speech TTS icon

Yandex Speech TTS

Преобразование текста в речь в сервисе Yandex SpeechKit

Yandex Speech TTS

AI-generated

Summary

Synthesizes the required text into speech with Yandex SpeechKit and returns the audio as binary data, along with its filename and timing metadata.

Inputs

  • text (required) — Text to synthesize; the operation rejects text longer than 250 characters.
  • voice — Voice for the synthesis: Alena, Jane, John, Zahar, Masha, Omazh, or Filipp. Defaults to Alena.
  • containerType — Audio format: MP3, OGG Opus, or WAV. Defaults to WAV.
  • yandexSpeechApi credentials (required) — Yandex Speech API credentials containing the API key.

Output shape

A single n8n item with JSON metadata and binary audio.

JSON contains fileName, startMs, and lengthMs. Binary audio is in the data property, named synthesized_track.mp3, synthesized_track.ogg, or synthesized_track.wav according to the selected format. API or malformed-response errors are raised as node errors.

Links

Discussion