Natural multilingual text-to-speech with 40+ voices and tone control.

ByteDance TTS 2.0

Voice preset. Parentheses show supported languages — use matching text (and Language when Auto fails).

Stokie (EN)

Dacey (EN)

Tim (EN)

Vivi (EN/ZH/JA/ES/ID)

Mindy (EN/ES/ID/PT/ZH)

Kian (EN/ZH)

Cedric (EN/ZH)

Sophie (EN/ZH)

Jean (EN/ZH)

Magnus (EN/ZH)

Mabel (EN/ZH)

Nadia (EN/ZH)

Opal (EN/ZH)

Pearl (EN/ZH)

Quentin (EN/ZH)

Vienna (EN/ZH)

Alina (EN/ZH)

Corinne (EN/ZH)

Esther (EN/ZH)

Freya (EN/ZH)

Gigi (EN/ZH)

Holly (EN/ZH)

Lyla (EN/ZH)

Daisy (EN/ZH)

Tracy (ES/ZH)

Jess (JA/ES/ID/PT/EN/ZH)

Pinky (ES/KO/EN/ZH)

Sweety (JA/ES)

Sandy (ES/EN/ZH)

Sven (DE)

Minimi (JA)

Usseau (FR)

Felipe (ES)

Han (ID)

Martins (PT)

Enzo (IT)

Shane (KO)

Felix (ZH)

Celeste (ZH)

Monkey King (ZH)

Optional natural-language instruction that steers delivery. Not spoken aloud.

Speech speed. 1.0 is normal, 0.5 half, 2.0 double.

Volume. 1.0 is normal, 0.5 half, 2.0 double.

Voice pitch shift in semitones. 0 is normal, -12/12 is one octave.

Opus

8 kHz

16 kHz

22 kHz

24 kHz

32 kHz

44 kHz

48 kHz

Force a reading language. Some voices (e.g. Sweety JA/ES) need this set — Auto may fail for them.