Yandex Cloud SpeechKit icon

Yandex Cloud SpeechKit

Synthesize speech using Yandex SpeechKit TTS API

Speech → Synthesize

AI-generated

Summary

Convert input text into a speech audio file using Yandex Cloud SpeechKit Text-to-Speech API.

Inputs

  • Text (required) — The text string to be converted into spoken audio.
  • Voice — Choose the voice character for the speech synthesis, including several male and female options with different languages.
  • Role — Select an emotional tone or role for the voice, such as Neutral, Good, or Evil.
  • Audio Format Type — Specify whether the output audio should be in a container format (WAV, MP3, OGG) or raw PCM format.
  • Container Type — If Container format is selected, choose the audio container type (WAV, MP3, OGG Opus).
  • Sample Rate — If Raw PCM format is selected, choose the sample rate for the audio output.
  • Additional Options — Optional parameters to adjust speech speed (0.1 to 3.0), volume (ranging from -145 to 1 depending on normalization), and pitch shift (-1000 to 1000 Hz).

Output shape

a list of items, one per input; each includes JSON metadata and binary audio data

Each output item contains metadata about the synthesis (success flag, input text, voice, role, audio format, audio size) in JSON, and the synthesized audio as a binary file under 'data'. The audio file extension and MIME type correspond to the selected output format. Errors return JSON with success: false and an error message. The operation supports multiple input items and handles each independently, with optional continue-on-fail behavior.

Links

Discussion