Using Accents and Languages

Supported Languages

Jellypod supports 70+ languages, including:

English, Spanish, French, Hindi, Portuguese, Chinese, German, Japanese, Arabic, Russian, Korean, Indonesian, Italian, Dutch, Turkish, Polish, Swedish, Filipino, Malay, Romanian, Ukrainian, Greek, Czech, Danish, Finnish, Bulgarian, Croatian, Slovak, and Tamil.

How Accents Work

Every voice in the Voice Library can speak all supported languages. The Accent shown in the Voice Library determines how the voice sounds, not which languages it can produce.

For example, a voice with a Spanish accent will speak English with a Spanish accent, and will sound fully native when generating Spanish content.

Selecting a Language

When creating a host, the language is determined by the voice you select:

1. On the Voice Type step, choose Voice Library.
2. In the Voice Library, use the Language dropdown to narrow the list to a language, or the Accent dropdown to narrow to a regional accent (the Language dropdown only appears when the library has voices in more than one language; the Accent dropdown only appears when the selected language has more than one regional accent to choose between). You can also type a language or accent name into the page's search bar.
3. Select a voice with the language or accent you want.

The Voice Library automatically sorts voices for your country: voices in your country's accent come first (American English for the United States, British English for the United Kingdom, and so on), then other voices in your language, then the rest of the catalog. If your country isn't recognized, it falls back to sorting by your browser's language setting instead.

Voice Quality Across Languages

Jellypod's Horizon audio model powers every voice in the library and handles emotion, pacing, and emphasis across languages. For Voice Library voices, the model is selected automatically based on the voice you choose, so there is nothing to configure.

If you record a new voice clone, the Voice style step lets you choose between More Consistent (most stable delivery) and More Expressive (more dynamic and emotive). For multilingual content, either style works; pick the one that sounds closest to what you want.

Frequently Asked Questions

Can one voice speak multiple languages?

Yes. Every voice in the Voice Library can speak all 29+ supported languages. The accent only determines how the voice sounds, not which languages it can produce.

Do I need to change a voice model setting for non-English episodes?

No. For Voice Library voices the model is selected automatically, so there is no separate setting to change. Every Voice Library voice can speak all supported languages, and its accent determines how it sounds. When you record a new voice clone, the Voice style step lets you pick between More Consistent and More Expressive.