Italian text-to-speech
Italian runs on five engines — both Qwen3-TTS variants, Chatterbox Multilingual, TADA's multilingual build and Kokoro — which puts it in the same tier of coverage as Spanish and French.
Kokoro provides two Italian preset voices, one female and one male, which is the smallest balanced pair in its catalogue and enough for most dialogue work. Qwen3-TTS accepts Italian but ships no natively Italian preset speaker, so a specific Italian voice means cloning. Italian is Latin-script, so long scripts chunk the way English does; if you are producing long-form narration, engine choice matters more for prosody over paragraphs than for anything mechanical.
The engines that speak Italian
- Qwen3-TTS
- Qwen3-TTS CustomVoice
- Chatterbox Multilingual
- TADA
- Kokoro
Every engine on that list is on the same plan — there is no per-engine surcharge and no tier that unlocks one. You choose per generation.
One caveat on TADA: it ships in two sizes and only the larger, multilingual build speaks Italian. Its smaller and faster model is English-only, so a Italian job has to be on the right one.
Voices you can start from
PRESET VOICES
Kokoro contributes 2 preset Italian voices. Qwen3-TTS CustomVoice ships no natively Italian preset speaker, so a preset used here is a voice speaking outside its own language.
YOUR OWN VOICE
Chatterbox Multilingual clones from a short reference clip in all 23 languages, Italianincluded — which is the answer whenever no preset is close enough. Cloning requires that the voice is your own or that you have the speaker’s explicit permission, on every plan.
Long Italian scripts
Italian is written in Latin script, so long scripts are split and stitched exactly the way English ones are, with no script-density adjustment needed. What varies over a long piece is prosody rather than mechanics — it is worth auditioning two engines on a real paragraph rather than on one line.
One plan, every engine and every language: $8 a month for 2 hours of generated audio, with a 7-day free trial.
Engine coverage on this page is pinned to the studio’s own language map by a cross-package test, so it cannot drift from what you are actually offered. See the engines page for what maintaining them involves, and audio rights for what you may do with the result.