Convert Short Text to Speech

Description

Convert short text to synthetic voice audio.

Project compatibility

Windows | Cross-platform

Configuration

• Connection ID - The connection established in Integration Service. Access the dropdown menu to choose, add, or manage connections.

• Text - Input the text or SSML to synthesize. The number of input characters is limited to 3,000 for text and 6,000 for SSML. This field supports String type input.
• Engine - Specifies the engine for Amazon Polly to use when processing input text for speech synthesis. Select one of the options from the dropdown list: Standard, Neural, Long-form. Default value is Standard.
• Language - Optional language code for the Synthesize speech request. This field is necessary only if using a bilingual voice, such as Aditi, which can be used for either Indian English (in-EN) or Hindi (hi-IN). Use the dropdown list to make your selection.
• Voice - The voice ID to use for the generation of output speech. Use the dropdown list to make your selection.
• Output speech format - Select the format in which the returned output will be encoded: OGG_VORBIS, PCM, MP3.
• Text type - Specifies whether the input text is plain text or SSML. Default value is: Text.

Manage Properties

Use the Manage Properties wizard to configure or use any of the object's standard or custom fields. You can select fields to add them to the activity canvas. The added standard or custom fields are available in the Properties panel (in Studio Desktop) or under Show additional properties (in Studio Web).

Additional properties

• Sample frequency - Select the audio frequency, in Hz, based on the output format. For MP3 and OGG_VORBIS, the valid values are "8000", "16000", "22050", and "24000". For standard voices, the default value is "22050". For PCM, the valid values are "8000" and "16000" (default). This field supports String type input.

Output

• Text to speech - Automatically generated output variable.