Speech synthesis using Playground

To convert text to speech via the SpeechKit Playground interface:

1. In the management console, select the folder you are going to use to work with SpeechKit.

2. In the list of services, select SpeechKit.

3. Navigate to the Speech synthesis tab.

4. Paste up to 5,000 characters of text into the central part of the window.

5. In the settings section on the left side of the window:

   • Pauses: Set up fixed pauses between words using tags, e.g., <[small]>, <[large]>. For a pause of a particular length, use the sil<[t]> tag, where t is the the pause length in milliseconds. The maximum value is 7,000.
   • Emphasize word: Accent a word using the <[accented]> tag or by enclosing it in asterisks (** **).
   • Stress: Mark the stressed vowel in homographs by prefixing it with +.
   • Phonemes: Tag words with [[]] to ensure proper pronunciation using phonemes.

6. Under Synthesis settings on the right side of the window:

   • Language: Set the speaker's language.
   • Voice: Select the speaker's voice.
   • Role: Control tone and emotion by selecting the speaker's role.
   • Speech speed: Set the speaker's speech rate in the range from 0.1 to 3.0, where 1.0 is the average human speech rate.
   • Voice pitch: Adjust the speaker's voice pitch. The higher the value, the greater the intonation contour of the synthesized audio in Hz.
   • Audio format: Select the audio format.

7. Click Synthesize and playback to synthesize speech.

8. To download the result, click .

SpeechKit Playground features basic speech synthesis options. For more flexible synthesis settings, use the API.