Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.beyondwords.io/llms.txt

Use this file to discover all available pages before exploring further.

Overview

BeyondWords offers voice support for 74 languages through ElevenLabs, with availability differing by voice model:
ModelDescriptionSupported languagesVoice options
v3Most expressive and dynamic output. Best for engaging, varied narration.74 languages
Multilingual v2Most stable and even output. Best for clear, consistent long-form narration.29 languages
Flash v2.5Most accurate and controlled output. Best for replicating specific voices and delivery styles.32 languages
All models are multilingual, meaning they can switch between all languages in your chosen model. However, voices typically perform best when used in their native language and accent (the language and accent of the audio they were trained with).

Language support by voice model

ElevenLabs v3 supports 74 languages: Afrikaans, Arabic, Armenian, Assamese, Azerbaijani, Belarusian, Bengali, Bosnian, Bulgarian, Catalan, Cebuano, Chichewa, Croatian, Czech, Danish, Dutch, English, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Hausa, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Kirghiz, Korean, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malay, Malayalam, Mandarin Chinese, Marathi, Nepali, Norwegian, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Serbian, Sindhi, Slovak, Slovenian, Somali, Spanish, Swahili, Swedish, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Vietnamese, Welsh. ElevenLabs Flash v2.5 supports 32 languages: Arabic, Bulgarian, Chinese, Croatian, Czech, Danish, Dutch, English, Filipino, Finnish, French, German, Greek, Hungarian, Hindi, Indonesian, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Romanian, Russian, Slovak, Spanish, Swedish, Tamil, Turkish, Ukrainian, Vietnamese. ElevenLabs Multilingual v2 supports 29 languages: Arabic, Bulgarian, Chinese, Croatian, Czech, Danish, Dutch, English, Filipino, Finnish, French, German, Greek, Hindi, Indonesian, Italian, Japanese, Korean, Malay, Polish, Portuguese, Romanian, Russian, Slovak, Spanish, Swedish, Tamil, Turkish, Ukrainian.

Accent support

Premade voices are available in a range of accents, depending on the language. For example, English includes voices with American, British, and Indian accents, among others. Voice generation can produce a wide range of accents based on your prompt. Broader accents (e.g., British English, American English) are generally more reliable, while highly specific regional accents (e.g., Boston English) may vary in quality or consistency. Voice cloning captures the accent of the original speaker, making it the best option for highly specific regional accents.

FAQs

If you can’t find the language you’re looking for, reach out to our sales team and we’ll see what we can do to help.
When you create a project in BeyondWords, you’ll set a primary language and accent (where applicable). This is used for AI preprocessing (if enabled), helping ensure words and phrases are pronounced correctly.Your selected language and accent act as default filters when choosing voices, but they won’t limit access to other languages or voices. If you change your default voice, your project’s default language and accent will update accordingly.
No, the BeyondWords dashboard is only available in English. You can use browser translation tools if you’d prefer to view the text in another language. 
A native voice speaks the language it was trained on, while a non-native voice speaks a language different from the original speaker’s.Non-native voices may carry traces of their native accent, but are often indistinguishable from native voices.