We’re excited to announce enhancements to Oracle Cloud Infrastructure (OCI) Speech’s text-to-speech (TTS) capabilities, now offering a broader selection of voices. With the original standard female voice, we’ve expanded our English options with the following voices to enrich your application integration.

  • Standard TTS voice: We’ve introduced a male voice to the standard TTS model.
  • Natural TTS voice: Utilizing neural network-based synthesis, our natural TTS voices deliver higher quality, more natural, expressive, and engaging audio. We’ve added both a male and a female natural TTS voice to this feature.

With these new voices, we’ve optimized the compute infrastructure for the managed service, significantly improving overall TTS responsiveness.

This enhanced TTS feature is available in the Phoenix (PHX) region upon request, with all new voices ready for seamless application integration. You can access the TTS feature through the Oracle Cloud Console.

Other functionalities include support for Speech Synthesis Markup Language (SSML), allowing you to control pauses, acronym abbreviations, and prosody in the generated speech using tags.

Figure 1: Covert text to speech in OCI console using the TTS feature
Figure 1: Covert text to speech in the Oracle Cloud Console using the TTS feature

Key features and benefits

This expansion offers the following features and benefits:

  • Natural speech conversion: Convert your text into speech that closely matches natural intonation and emotion. Input text through the Console or API request, and the neural TTS engine generates a naturally sounding voice as the output.
  • Streaming support: By default, the TTS engine generates voice after receiving the entire text. For a smoother user experience, enable streaming mode to generate voice output as soon as partial text is received.
  • Extensive SSML tag support: Gain precise control over the generated voice with support for various SSML tags. For detailed usage instructions, refer to built-in examples in the Console. 
Figure 2: Available SSML tags when using TTS
Figure 2: Available SSML tags when using TTS

 

  • SDK and API Support: Integrate TTS using the software developer kit (SDK) and API. Detailed integration instructions are available in the API documentation.

These features enhance the user experience by delivering high-quality, natural-sounding speech and flexible integration options.

What to know more?

The OCI Speech service team is committed to empowering you with tools that redefine possibilities, and we look forward to seeing you using the newly introduced TTS feature in your integration with OCI. Stay tuned for the availability announcement of real time transcription with customized vocabulary.

If you’re new to Oracle Cloud Infrastructure, try Oracle Cloud Free Trial, a free 30-day trial with US$300 in credits.

For more information, see the following resources: