--- title: "Aura-2 (TTS) now speaks Dutch, French, German, Italian, and Japanese" description: "Deepgram expands its high-precision text-to-speech API to bring natural, business-ready voice infrastructure to global markets." canonical: "https://deepgram.com/blog/aura-2-now-speaks-dutch-french-german-italian-japanese" authors: - "Hasan Jilani" date: "2025-12-15" category: "Announcements" --- # Aura-2 (TTS) now speaks Dutch, French, German, Italian, and Japanese Text-to-speech has become a cornerstone of voice AI, powering everything from scheduling assistants to customer support agents and multilingual automation. Aura-2 delivers the natural and realistic speech users expect, but it is also engineered for the rigorous demands of business use cases. Beyond human-like intonation, it prioritizes clarity, precision, and responsiveness. These qualities are essential for real-time voice agents where accuracy and speed are just as critical as voice quality. Today, we are excited to announce that Aura-2 now supports five additional languages: 🇳🇱 **Dutch** 🇫🇷 **French** 🇩🇪 **German** 🇮🇹 **Italian** 🇯🇵 **Japanese** These join our existing English and Spanish models to provide a robust infrastructure for global voice applications. This expansion helps developers deliver consistent, multilingual voice experiences via our API without sacrificing naturalness, pronunciation accuracy, or low-latency performance. ## Why these languages matter for TTS Each new Aura-2 language inherits unique phonological and prosodic challenges that make high-quality TTS difficult. However, getting these details right is critical for business applications where clarity prevents costly errors. Here is why these languages are impactful additions: **Dutch sample (nl)** - [Dutch](https://cdn.sanity.io/files/zf5tfwjf/production/b13a66f7f2562c32aec9681df973c94ba6a4b998.mp3) Sample: “Uw reserveringsnummer is 8 4 9 2 B.” EN: Your reservation number is 8492B. **🇳🇱 Dutch: Vowel richness and compound-heavy words** Dutch has long vowels, diphthongs, and ultra-long compound nouns. Natural TTS must handle stress placement and smooth glides between complex vowel forms while keeping numeric data clear. --- **French sample (fr)** - [French](https://cdn.sanity.io/files/zf5tfwjf/production/2eff75ca38baa9083c943fc7e4f2ab1263163f8a.mp3) Sample: “Veuillez appeler le 01 23 45 67 89 pour confirmer.” EN: Please call 01 23 45 67 89 to confirm. **🇫🇷 French: Liaison, elision, and continuous flow** French uses fluid connected speech (liaisons) and dropped sounds (elisions). This requires a TTS engine to master subtle transitions without sounding choppy, especially when reading strings of numbers like contact information. --- **German sample (de)** - [German](https://cdn.sanity.io/files/zf5tfwjf/production/fba57ccc0312e35e5fcf0ee131e687caf3010ed5.mp3) Sample: “Ihr Termin ist für den 24. Mai um 14:30 Uhr bestätigt.” EN: Your appointment is confirmed for May 24th at 14:30. **🇩🇪 German: Precision with long compounds and consonant clusters** German’s long words, clustered consonants, and consistent stress rules demand a voice model that enunciates clearly without sounding robotic. This is vital for complex scheduling and time-based data. --- **Italian sample (it)** - [Italian](https://cdn.sanity.io/files/zf5tfwjf/production/b7409372ed19847e6124fb1924fcaac3b89c9853.wav) Sample: “Il numero di riferimento è 1250.” EN: “The reference number is 1250.” **🇮🇹 Italian: Open vowels and musical intonation** Italian TTS must preserve melody and vowel openness without exaggeration. Aura-2 maintains the natural rhythm of Italian speech even when delivering transactional updates involving currency. --- **Japanese sample (ja)** - [Japanese](https://cdn.sanity.io/files/zf5tfwjf/production/55cb192de627a59921fcdbbd370b4527ca2ec197.mp3) Sample: “認証コード 7 3 9 1 を入力してください。” EN: Please enter authentication code 7391. **🇯🇵 Japanese: Politeness markers, pitch accent, and mixed scripts** Japanese blends kanji, kana, and loanwords while relying heavily on pitch accent. Aura-2 ensures smooth phrasing and consistent tone. This is also a strong example of structured-speech correctness, where the model must seamlessly switch between Japanese script and alphanumeric codes. --- ## Human preference results for conversational voice In addition to audio samples and system-level performance metrics, we evaluate Aura-2 using blind human preference testing focused specifically on conversational voice quality. In these evaluations, human annotators compared voices from three vendors at a time and selected the voice that sounded most natural for conversational use cases such as customer service, interviews, and casual dialog. Each evaluation produced a single winner, resulting in a random baseline win rate of 33.3%. The charts below highlight conversational performance by language, reflecting how well Aura-2 aligns with real-world expectations for interactive voice applications. ![](https://cdn.sanity.io/images/zf5tfwjf/production/e9065c36f61e357b06f8549b697422c9cfd59491-1999x1198.png) ![](https://cdn.sanity.io/images/zf5tfwjf/production/08f8ef9d68e5716c569188c70628595dbc015a3a-1600x1335.png) ![](https://cdn.sanity.io/images/zf5tfwjf/production/e17be056327f3219537f9e11f206040e6f6c60ea-1600x1167.png) ![](https://cdn.sanity.io/images/zf5tfwjf/production/00e996999fff77b1981c5df718af5e6f7cd22d94-1600x1167.png) **_About these evaluations:_** _Results are based on blind human preference testing for conversational voice prompts. Each evaluation compares three vendors and produces a single preferred voice (random baseline: 33.3%). Charts show conversational win rates by language._ #### What the results show Across the languages highlighted here, Aura-2 demonstrates strong conversational preference in scenarios that prioritize clarity, pacing, and consistency over exaggerated expressiveness. - **Dutch:** Aura-2 ranks first in conversational preference, with the highest win rate among evaluated vendors. - **German, Italian, Spanish, and Japanese:** Aura-2 consistently ranks among the top conversational voices, indicating strong alignment with customer-service and interactive speech expectations across multiple language families. These results reflect Aura-2’s design focus on business-ready conversational speech, where voices must sound natural, reliable, and intelligible over extended interactions. ## Unified infrastructure for global scale Aura-2 continues to evolve as a unified voice synthesis infrastructure for global products and workflows. Instead of applying a single prosodic pattern to every language, Aura-2 adapts to each language’s unique phonology, whether it involves pitch accents, liaisons, or compound stress rules. For developers and enterprise teams, this means: - **Consistent performance** across diverse global markets via a single API. - **High-precision pronunciation** for structured data like IDs, currency, and times. - **Sub-200ms latency** that ensures fluid, real-time conversational flow. - **High reliability under streaming loads** with stable performance even during high-volume concurrency. - **Simplified infrastructure** that eliminates the need to stitch together different vendors for different languages. ## Getting started Switching to any of the newly supported languages is simple. Update your API request with the appropriate language code. **Bash** ```bash curl https://api.deepgram.com/v1/speak \ -H "Authorization: Token YOUR_DEEPGRAM_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "aura-2", "language": "fr", "text": "Bonjour, comment puis-je vous aider ?" }' ``` **New language codes:** ```text nl, fr, de, it, ja ``` For a complete list of available voices and to hear audio samples for each region, refer to the [TTS Voices and Languages documentation](https://developers.deepgram.com/docs/tts-models). You can also visit the [Deepgram Playground](https://playground.deepgram.com/?endpoint=speak&architecture=aura-2&language=nl) to input your own text and test performance in real-time. ## Looking ahead With five new languages now live, Aura-2 continues its progress toward full global coverage. Accuracy, adaptability, and real-time reliability continue to improve across language families and acoustic environments. The goal is clear: voice AI that works everywhere, for everyone. We are building text-to-speech that sounds natural, responds instantly, and works globally, regardless of the complexity of the business use case. ## Unlock enterprise-grade voice AI today Sign up free and unlock $200 in credits, enough to generate over 13 million characters of synthesis. Explore details on our [TTS Voices and Languages](https://developers.deepgram.com/docs/tts-models) page and hear Aura-2’s natural, high-precision performance for yourself. ## Related articles - Anam solves turn-taking for unscripted avatar conversation with Flux STT (AI Agents) - Audio, decision, composition: Five open-source Jev projects (AI Engineering & Research) - Introducing Nova-3 Medical multilingual: Medical speech recognition in 10 languages (Announcements) - AI voice agent to human handoffs: How to warm transfer calls without losing context (AI Engineering & Research)