Speech synthesis

Speech synthesis allows:

• voice your text;
• create a recording of voice messages in different languages ​​(english, ukrainian, russian);
• use different male and female voices;
• use ready-made voice messages from our library;
• upload your files (user voice messages);
• make flexible settings (pauses, volume, pitch, and voice playback speed).

How it works?

• In the personal account of the UniTalk user, go to the section IP-telephony – Audio synthesis.
• In the synthesis window, add text in text or ssml format (no more than 5000 characters).
• Make settings: specify the time for a pause before the text, select the required language, and select the quality and gender of the voice.
• After that, press the “Synthesize” button and the TTS (Text to Speech) function will convert a text message into a voice message.

Additional settings for speech synthesis.

• Audio profile selection: 8 types of sound effects that are superimposed on audio (headphones, smart watches, TV, etc.).
• Sample Rate (Hz): The sample rate of the synthesized audio.
• Volume change (dB): -96 to +16.
• Voice Pitch: Depending on the value specified, the voice will sound higher or lower.
• Text reading speed: x0.25 will be 4 times slower than usual, and x3 will be 3 times faster than usual.

Versatility and flexibility of speech synthesis technology:

• can be used in API calls, phone auto dialing, predictive dialing, interactive voice menu – IVR;
• you can play both ready-made voice messages and voice information in real-time (for example voice the amount on the client’s balance or the status of his order).