Multilingual voice cloning
One cloned voice speaks across every supported language.
- Cloned voice works across 30+ languages
- Powered by simba-multilingual
- One voice ID for every language
- Consent required
Definition
Multilingual voice cloning lets a single cloned voice speak across all 30+ supported languages. Powered by simba-multilingual, one voice ID covers every language, so you clone once, with consent, and synthesize that voice in any market rather than cloning a separate voice per language.
One voice many languages
The point is identity across languages. A cloned voice run through simba-multilingual keeps its character while speaking a translated script, which is what makes it useful for dubbing and localized editions. See the dubbing page.
The model
Cloned voices run self-serve on simba-english, simba-multilingual, and simba-3.0. simba-multilingual is the one that unlocks the full language set for a clone. The curated simba-3.2 voice set plays cloned voices too, but each one currently requires manual Speechify approval - choose simba-multilingual for cross-language cloning without that step.
Clone once
You do not clone per language. A single voice ID handles every supported language, so localizing is a synthesis job, not a repeat of the cloning step. See the language support.
Consent
A consent record with the speaker’s full name and email is required to create the voice. See the TTS multilingual page for the underlying language reach.
Frequently asked questions
Can a cloned voice speak multiple languages?
Which model powers multilingual cloning?
Do I clone once or per language?
Start building
One cloned voice speaks across every supported language.