Generating Text to Speech Output

Generate audio from text with the Speech service.

For more information about this feature, see Using Text to Speech.

    1. Open the navigation menu  and select Analytics & AI. Under AI Services, select Speech.
    2. Select Text to speech.
    3. On the Text to speech page, under Input text, enter the text to generate as speech.
    4. Under Settings, enter the following information.
      • Compartment: Select the compartment that you want to work in.
      • Model type: Select Natural for a natural, human sounding voice, or Standard for a machine sounding voice.
      • Language: Default: English (United States).
      • Speaker: Select a speaker.
      • Output format: Select the audio format for the output.
      • Sample rate: Enter the sample rate for the audio output. You can enter a value between 8000 and 48000 hertz.
      • Streaming (Optional)
      • SSML (Optional) (available for some speakers): Use Speech Synthesis Markup Language (SSML) with the specified example (SSML examples) in the text-to-speech request.

        The selected example appears in the Input text area. For information about tags and attributes available for SSML, see SSML Tags.

    5. Select Generate.
      Generated speech is shown under Audio output.
    • To download the generated audio, select Actions and then select Download Audio.
    • To view the generated JSON file, select Actions and then select View JSON (available when JSON is selected for Output format).
    • To reset the input text and start over, select Reset.
  • Use the oci speech synthesize-speech command and required parameters to generate text to speech output:

    oci speech synthesize-speech --file [file] --text [text] ... [OPTIONS]

    For a complete list of parameters and values for CLI commands, see the CLI Command Reference.

  • Use the SynthesizeSpeech operation to generate text to speech output.