Text-to-Speech Voices in Logic+

Overview

Logic+ supports text-to-speech (TTS) across a wide range of languages, regional dialects, and voice types, allowing you to deliver a localized and natural-sounding experience to customers. Voices can be specified directly by name or referenced through variables within a Logic+ flow. This article covers voice naming conventions, available voice types, and the complete list of supported languages and voices sourced from AWS Polly.

Voice Naming Format for Variables

When referencing a voice by name within a Logic+ variable, the following formatting rules apply:

• The first letter of the voice name must be capitalized.

• Diacritics must be removed — accents, tildes, and other marks are not supported in variable references.

• When referencing a voice variant, append the variant type in parentheses exactly as shown — for example, Joanna (neural) or Danielle (generative).

Examples:

• The Brazilian Portuguese voice Vitória should be written as Vitoria in a variable.

• The French voice Léa should be written as Lea in a variable.

Voice Types

Each voice may be available in one or more of the following variants. Where multiple variants exist for the same voice, the variant type is shown in parentheses next to the voice name. When no variant is specified, the voice uses the standard engine.

• Standard

  • The base text-to-speech voice using concatenative synthesis. Suitable for most general use cases.

• Neural

  • Uses deep learning models to produce more natural-sounding, expressive speech compared to standard voices. Recommended over standard where available.

• Long-form

  • Optimized for longer content such as extended prompts or detailed messages. Produces more natural pacing and intonation over longer passages.

• Generative

  • Uses generative AI to produce the most natural, human-like speech quality available. Best suited for scenarios where the highest level of voice realism is required.

Available Languages and Voices

Arabic arb

Arabic (Gulf) ar-AE

Catalan ca-ES

Chinese (Cantonese) yue-CN

Chinese (Mandarin) cmn-CN

Czech cs-CZ

Danish da-DK

Dutch nl-NL

Dutch (Belgian) nl-BE

English (Australian) en-AU

English (British) en-GB

English (Indian) en-IN

English (Ireland) en-IE

English (New Zealand) en-NZ

English (Singaporean) en-SG

English (South African) en-ZA

English (US) en-US

English (Welsh) en-GB-WLS

Finnish fi-FI

French fr-FR

French (Belgian) fr-BE

French (Canadian) fr-CA

German de-DE

German (Austrian) de-AT

German (Swiss) de-CH

Hindi hi-IN

Icelandic is-IS

Italian it-IT

Japanese ja-JP

Korean ko-KR

Norwegian nb-NO

Polish pl-PL

Portuguese (Brazilian) pt-BR

Portuguese (European) pt-PT

Romanian ro-RO

Russian ru-RU

Spanish (Spain) es-ES

Spanish (Mexican) es-MX

Spanish (US) es-US

Swedish sv-SE

Turkish tr-TR

Welsh cy-GB

* Bilingual voice — supports more than one language. ** Supports the Newscaster speaking style when used with the Neural engine.