> This is a page from the ElevenLabs documentation. For a complete page index, fetch https://elevenlabs.io/docs/llms.txt. For the full documentation in a single file, fetch https://elevenlabs.io/docs/llms-full.txt.

# What models do you offer and what is the difference between them?

##

**Flagship Models**
\


**Eleven v4 (model\_id = eleven\_v4)**- Eleven v4 is our latest and most advanced speech
synthesis model. It is a state-of-the-art model that produces natural, life-like speech with high
emotional range and contextual understanding across multiple languages.

For UI generations, 1 character costs 1 credit, excluding credit multipliers. API generations are discounted - for details, see our [API Pricing.](https://elevenlabs.io/pricing)\
\
Eleven v4 supports 90+ languages:

* **AFR** Afrikaans
* **AMH** Amharic
* **ARA** Arabic
* **HYE** Armenian
* **ASM** Assamese
* **AST** Asturian
* **AZE** Azerbaijani
* **BEL** Belarusian
* **BEN** Bengali
* **BOS** Bosnian
* **BUL** Bulgarian
* **MYA** Burmese
* **YUE** Cantonese
* **CAT** Catalan
* **CEB** Cebuano
* **HRV** Croatian
* **CES** Czech
* **DAN** Danish
* **NLD** Dutch
* **ENG** English
* **EST** Estonian
* **FIL** Filipino
* **FIN** Finnish
* **FRA** French
* **FUL** Fula (Pulaar)
* **GLG** Galician
* **KAT** Georgian
* **DEU** German
* **ELL** Greek
* **GUJ** Gujarati
* **HAU** Hausa
* **HEB** Hebrew
* **HIN** Hindi
* **HUN** Hungarian
* **ISL** Icelandic
* **IND** Indonesian
* **ITA** Italian
* **JPN** Japanese
* **JAV** Javanese
* **KAM** Kamba
* **KAN** Kannada
* **KAZ** Kazakh
* **KOR** Korean
* **KIR** Kyrgyz
* **LAO** Lao
* **LAV** Latvian
* **LIN** Lingala
* **LIT** Lithuanian
* **LUG** Luganda
* **LTZ** Luxembourgish
* **MKD** Macedonian
* **MSA** Malay
* **MAL** Malayalam
* **MLT** Maltese
* **CMN** Mandarin Chinese
* **MRI** Māori
* **MAR** Marathi
* **MON** Mongolian
* **NEP** Nepali
* **NOB** Norwegian Bokmål
* **OCI** Occitan
* **ORI** Odia
* **PUS** Pashto
* **FAS** Persian
* **POL** Polish
* **POR** Portuguese (Brazil)
* **PAN** Punjabi
* **RON** Romanian
* **RUS** Russian
* **SRP** Serbian
* **SNA** Shona
* **SND** Sindhi
* **SLK** Slovak
* **SLV** Slovenian
* **SOM** Somali
* **CKB** Sorani Kurdish
* **SPA** Spanish (LatAm)
* **SWA** Swahili
* **SWE** Swedish
* **TGK** Tajik
* **TAM** Tamil
* **TEL** Telugu
* **THA** Thai
* **TUR** Turkish
* **UKR** Ukrainian
* **URD** Urdu
* **UZB** Uzbek
* **VIE** Vietnamese
* **CYM** Welsh
* **WOL** Wolof
* **ZUL** Zulu

**Multilingual v2 (model\_id = eleven\_multilingual\_v2)** - Multilingual v2 is our most
life-like, emotionally rich model. It's best for voiceovers, audiobooks, and content creation.

For UI generations, 1 character costs 1 credit, excluding credit multipliers. API generations are discounted - for details, see our [API Pricing.](https://elevenlabs.io/pricing)

Multilingual v2 supports 29 languages:

* **ARA** Arabic
* **BUL** Bulgarian
* **CMN** Chinese
* **HRV** Croatian
* **CES** Czech
* **DAN** Danish
* **NLD** Dutch
* **ENG** English
* **FIL** Filipino
* **FIN** Finnish
* **FRA** French
* **DEU** German
* **ELL** Greek
* **HIN** Hindi
* **IND** Indonesian
* **ITA** Italian
* **JPN** Japanese
* **KOR** Korean
* **MSA** Malay
* **POL** Polish
* **POR** Portuguese
* **RON** Romanian
* **RUS** Russian
* **SLK** Slovak
* **SPA** Spanish
* **SWE** Swedish
* **TAM** Tamil
* **TUR** Turkish
* **UKR** Ukrainian



**Flash v2.5 - (model\_id = eleven\_flash\_v2\_5) -** our latest, ultra-low-latency model,
generating speech in under 75ms.  Best for developer use cases requiring speed and multiple
languages.

For UI generations, 1 character costs 1 credit, excluding credit multipliers. API generations are discounted - for details, see our [API Pricing.](https://elevenlabs.io/pricing)

It supports 32 languages:

* **ARA** Arabic
* **BUL** Bulgarian
* **CMN** Chinese
* **HRV** Croatian
* **CES** Czech
* **DAN** Danish
* **NLD** Dutch
* **ENG** English
* **FIL** Filipino
* **FIN** Finnish
* **FRA** French
* **DEU** German
* **ELL** Greek
* **HUN** Hungarian
* **HIN** Hindi
* **IND** Indonesian
* **ITA** Italian
* **JPN** Japanese
* **KOR** Korean
* **MSA** Malay
* **NOR** Norwegian
* **POL** Polish
* **POR** Portuguese
* **RON** Romanian
* **RUS** Russian
* **SLK** Slovak
* **SPA** Spanish
* **SWE** Swedish
* **TAM** Tamil
* **TUR** Turkish
* **UKR** Ukrainian
* **VIE** Vietnamese



**Flash v2 - (model\_id = eleven\_flash\_v2)**- our latest, ultra-low-latency English-only
model, generating speech in under 75ms.  Best for developer use cases requiring speed.

For UI generations, 1 character costs 1 credit, excluding credit multipliers. API generations are discounted - for details, see our [API Pricing.](https://elevenlabs.io/pricing)

* **ENG** English



## **Older Models**

**These models are maintained for backward compatibility but are not recommended for new projects**

**Turbo v2.5** - **(model\_id = eleven\_turbo\_v2\_5)**- Eleven Turbo v2.5 is
our high-quality, low-latency model with a good balance of quality and speed. As the Flash models
give very similar results, we recommend using the Flash models over Turbo.

For UI generations, 1 character costs 1 credit, excluding credit multipliers. API generations are discounted - for details, see our [API Pricing.](https://elevenlabs.io/pricing)

It supports 32 languages, including:

* **ARA** Arabic
* **BUL** Bulgarian
* **CMN** Chinese
* **HRV** Croatian
* **CES** Czech
* **DAN** Danish
* **NLD** Dutch
* **ENG** English
* **FIL** Filipino
* **FIN** Finnish
* **FRA** French
* **DEU** German
* **ELL** Greek
* **HUN** Hungarian
* **HIN** Hindi
* **IND** Indonesian
* **ITA** Italian
* **JPN** Japanese
* **KOR** Korean
* **MSA** Malay
* **NOR** Norwegian
* **POL** Polish
* **POR** Portuguese
* **RON** Romanian
* **RUS** Russian
* **SLK** Slovak
* **SPA** Spanish
* **SWE** Swedish
* **TAM** Tamil
* **TUR** Turkish
* **UKR** Ukrainian
* **VIE** Vietnamese



**Turbo v2 (model\_id = eleven\_turbo\_v2)** - As the Flash models give very similar
results, we recommend using the Flash models over Turbo.

For UI generations, 1 character costs 1 credit, excluding credit multipliers. API generations are discounted - for details, see our [API Pricing.](https://elevenlabs.io/pricing)

* **ENG** English

> ElevenLabs provides APIs and SDKs for text to speech, voice cloning, speech to text, sound effects, voice isolator, voice changer, and conversational AI agents. Build voice-enabled applications with lifelike audio generation.