San Jose, CA



Core technologies: Speech synthesis (TTS)

Scope: Specialized (SPC)

System: On-Premises (PRM), Edge


  • Speechmorphing provides text-to-speech (TTS) synthesis solutions, including customized voices.
  • The customization is said to require only 5 to 10 minutes of voice recordings and a few days.
  • The company’s “Smorph expressive voices” are said to respond with “prosodic modeling” to allow changing speaking styles.
  • The solution is suitable for interactive marketing, conversational IVR, conversational bots, home security bots that speak in the homeowner’s voice, and home care bots.
  • Speechmorphing works with application, device, and bot developers for global markets.

Delving Deeper

Speechmorphing text-to-speech synthesis provides the basic ability to convert text to natural sounding speech, but they emphasize their ability to provide customized, branded TTS voices from only five to ten minutes of speech from a speaker. The system starts with existing or new recordings of the brand voice.

Alternatively, a company can customize a pre-built voice with styles and domains, from tones and demeanor to pronunciation and lingo. Granular controls within the text allow further adjusting the mood, volume, pitch, speed, intonation and “sound gestures.”

Once created, a TTS voice can be integrated with chatbots or other voice user interfaces.