SpeechifyAI Build Language Support

SpeechifyAI Build models support synthesizing speech in multiple languages. The API handles both single-language texts and mixed-language inputs.

Non-English synthesis requires simba-3.0 or simba-multilingual. simba-3.2 and simba-english are English-only; a non-English voice on them returns 400.

Which model covers which languages

Model	Languages
`simba-3.0`	English plus German, Spanish (Spain and Mexico), French, Italian and Brazilian Portuguese. See Simba 3.0 languages
`simba-multilingual`	The full 30+ locale set below
`simba-3.2`, `simba-english`	English only

Simba 3.0 languages

simba-3.0 is streaming-native and officially supports these seven locales:

Language	Code
English	en-*
German	de-DE
Spanish (Spain)	es-ES
Spanish (Mexico)	es-MX
French	fr-FR
Italian	it-IT
Portuguese (Brazil)	pt-BR

You select the language with the language request parameter; when you omit it, the model is chosen from the voice’s own locale. simba-3.0 routes English to its English training and everything else to its multilingual one, so this is an internal detail: the model ID you pass never changes.

Languages outside this list often still produce usable audio on simba-3.0, but they are not validated or officially supported. Use simba-multilingual for the full locale set below.

Fully Supported Languages

The following languages are fully supported for speech synthesis:

Language	Code
English	en
French	fr-FR
German	de-DE
Spanish	es-MX
Portuguese (Brazil)	pt-BR
Portuguese (Portugal)	pt-PT

Beta Languages

The following languages are currently in beta (we’re actively improving them and welcome feedback):

Language	Code
Arabic	ar-AE
Bengali	bn-IN
Cantonese	yue-CN
Danish	da-DK
Dutch	nl-NL
Estonian	et-EE
Finnish	fi-FI
Greek	el-GR
Gujarati	gu-IN
Hebrew	he-IL
Hindi	hi-IN
Italian	it-IT
Japanese	ja-JP
Korean	ko-KR
Marathi	mr-IN
Norwegian	nb-NO
Polish	pl-PL
Russian	ru-RU
Swedish	sv-SE
Tamil	ta-IN
Telugu	te-IN
Turkish	tr-TR
Ukrainian	uk-UA
Urdu	ur-IN
Vietnamese	vi-VN

Coming Soon

We will soon support these additional languages:

Language	Code
Belarusian	be-BY
Bulgarian	bg-BG
Catalan	ca-ES
Croatian	hr-HR
Czech	cs-CZ
Filipino	fil-PH
Georgian	ka-GE
Hungarian	hu-HU
Indonesian	id-ID
Malay	ms-MY
Mandarin	zh-CN
Nepali	ne-NP
Persian	fa-IR
Romanian	ro-RO
Serbian	sr-RS
Slovak	sk-SK
Thai	th-TH

Using the `language` Parameter

Our speech synthesis endpoints (/v1/audio/speech and /v1/audio/stream) support the optional language parameter, which should follow the locale naming standard (e.g., en-US, fr-FR).

When to specify the language:

Known single language: If you know the input text is entirely in one language, providing the language parameter will result in better audio quality.
Unknown or mixed language: If you’re unsure of the input language or the text contains multiple languages, omit the language parameter. Speechify models will automatically detect and handle the language(s) in the input.

Voice Cloning Languages

There are no language limitations for voice cloning. Speechify can produce high-quality cloned voices from short audio samples (10-30 seconds recommended) and use the same voice to synthesize speech in any supported language. See Voice Cloning for details.