Paradox Interactive
Power game worlds with natural AI voices
Our AI voices adapt to any character or setting, delivering natural speech in 32 languages that’s quick to implement and ready to scale with your game’s needs. Customize voices to fit unique personalities and make every character sound authentic
High quality, low latency Turbo model
Deliver fast, high-quality voice responses in your games. Our Turbo model ensures real-time performance, providing natural voices in text to speech for online gaming without delays or loss of quality, making interactions seamless and dynamic
Build faster than ever
Quickly generate AI voices in multiple languages for your game worlds, NPCs, and interactive content. Our text to speech for gaming integrates easily into your development workflow, offering fast voice generation with full multilingual support
Infinite selection of AI voices
Find the perfect voice for your character. Choose from thousands of voices in Voice Library or create new ones from scratch using Voice Design. Adjust age, accent, and tone to match your characters and fit the style of your game
Sound effects generator
Create distinctive sound effects directly from text descriptions, streamlining your audio production process. Get four samples within seconds, speeding up your selection and workflow. Add nuance through precise descriptions, tailoring each effect to fit your scene
Enterprise grade security
Our API is built for enterprise needs, ensuring robust security with SOC2 and GDPR compliance to protect your data and support your projects at scale
Localize games across 29 Languages
Localize your game easily with AI-powered dubbing. Players can enjoy your game in their native language, enhancing accessibility and expanding your reach
Afrikaans
Arabic
Armenian
Assamese
Azerbaijani
Belarusian
Bengali
Bosnian
Bulgarian
Catalan
Cebuano
Chichewa
Chinese
Croatian
Czech
Danish
Dutch
English
Estonian
Filipino
Finnish
French
Galician
Georgian
German
Greek
Gujarati
Hausa
Hebrew
Hindi
Hungarian
Icelandic
Igbo
Indonesian
Irish
Italian
Japanese
Javanese
Kannada
Kazakh
Kyrgyz
Korean
Latvian
Lingala
Lithuanian
Luxembourgish
Macedonian
Malay
Malayalam
Mandarin Chinese
Marathi
Nepali
Norwegian
Pashto
Persian
Polish
Portuguese
Punjabi
Romanian
Russian
Serbian
Sindhi
Slovak
Slovenian
Somali
Spanish
Swahili
Swedish
Tamil
Telugu
Thai
Turkish
Ukrainian
Urdu
Vietnamese
Welsh
How we support the best game studios and creatives in the world
GRANTS
Build natural voices into your product
✓ 11M Characters
✓ 3 months free
✓ Higher concurrency limits
Frequently asked questions
You can get started by signing up for a free account. Once you have an account, find your xi-api-key in your profile settings. This key is required for authentication in API requests. You can then generate audio from text in a variety of languages by sending a POST request to the API with the desired text and voice settings. The API returns an audio file in response. Use programming languages like Python for these requests.
Absolutely, we have extensive resources to help you with integration, an active developer community on Discord, and a responsive support team to assist you!
Usage-based billing offers a fixed price for each additional 1,000 credits used over your limit.
Your data security is our priority. Our API is designed with robust security in place, including SOC2 and GDPR compliance, an end-to-end encryption, and an optional no-retention mode.
Our Flash model API delivers audio at 128 kbps with ~75ms latency.
The ElevenLabs Grants program offers free usage plans to help startups and new products integrate lifelike voices into their applications. Recipients get three months of free usage, including over 200 hours of generated audio and access to high-scale capabilities and early features. This support lets startups to build, test, and launch their products with ElevenLabs voices without upfront costs.