Watson Developer Cloud

Text to Speech

Designed for streaming low-latency synthesis of audio from written text. The service synthesizes natural-sounding speech from input text in a variety of languages and voices that speak with appropriate cadence and intonation.

General Availability

Watson Text to Speech provides a REST API to synthesize speech audio from an input of plain text. Multiple voices, both male and female, are available across Brazilian Portuguese, English, French, German, Italian, Japanese, and Spanish. Once synthesized in real-time, the audio is streamed back to the client with minimal delay. The Text to Speech service now enables developers to control the pronunciation of specific words.

Intended Use

Anywhere there's a need to communicate using the spoken word, particularly assistance tools for the vision-impaired, reading-based education tools, or mobile applications.

You input

  • Brazilian Portuguese plain text
  • English plain text
  • French plain text
  • German plain text
  • Italian plain text
  • Japanese plain text
  • Spanish plain text

Service output

  • Brazilian Portuguese speech (1 female voice)
  • US English speech (choose between 3 voices: 2 female, 1 male)
  • UK English speech (1 female voice)
  • French speech (1 female voice)
  • German speech (choose between 2 voices: 1 female, 1 male)
  • Japanese speech (1 female voice)
  • Italian speech (1 female voice)
  • Castilian Spanish speech (choose between 2 voices: 1 female, 1 male)
  • North American Spanish speech (1 female voice)

Try it out

Check out the Text to Speech demo below. Enter your own text or choose the pre-entered text and select from the drop-down list which voice (language and gender) you want to generate the speech in. Then click "Download" to download the audio file or "Speak" to have the browser stream the audio. The application Watson Spoken Healthcare on the Watson Developer Cloud App Gallery also demonstrates the Text to Speech service..


Standard Service


First million characters per month are FREE. Additional characters are $0.02 per thousand.

Includes the ability to use any of the voices available in all supported languages.

Premium Plan

For customers with high requirements around information security, in regulated industries, or who handle highly sensitive data, Watson services are available through a Premium plan. These plans offer developers and organizations Watson services in a single tenant isolated model, including compute-level isolation at the VM and container levels. The Premium plan includes data encryption in transit and at rest that is offered in standard plans. For more information or to purchase a premium plan, contact us.

Ready to use?


Getting started is easy! Try out the service on Bluemix now.

Use In Bluemix


Ready to get down to the details? Full documentation detailing how to get started using this Service in Bluemix is available for each Watson service.

View full docs