- Newest
- Most votes
- Most comments
Nova Lite, Micro and Pro support 200+ languages. Nova Canvas and Reel support only English.
Amazon Nova models support a wide range of languages, with particularly strong capabilities in over 200 languages. The models are especially proficient in English, German, Spanish, French, Italian, Japanese, Korean, Arabic, Simplified Chinese, Russian, Hindi, Portuguese, Dutch, Turkish, and Hebrew. This multilingual support allows users to build truly global applications without worrying about language barriers or maintaining separate models for different regions.
However, it's important to note that the language support varies depending on the specific task. For understanding models, which accept text, image, or video inputs to generate text output, the full range of over 200 languages is supported. This means these models can process and understand content in all these languages for tasks like summarization, translation, content classification, and visual question-answering.
For creative content generation, such as image and video generation, the language support is more limited. Amazon Nova models for creative content generation specifically support English prompts. This means that while you can generate images or videos using Amazon Nova Canvas and Amazon Nova Reel, the text prompts used to guide this generation must be in English.
It's worth noting that the information provided does not specify language support for text-to-speech capabilities in Amazon Nova. The sources mainly focus on text, image, and video processing and generation, rather than audio or speech synthesis.
Sources
Introducing Amazon Nova: Frontier intelligence and industry leading price performance | AWS News Blog
answered 2 years ago
Relevant content
asked a year ago
asked a year ago
- AWS OFFICIALUpdated 7 days ago
- AWS OFFICIALUpdated 5 years ago
Of the 200+ languages supported by Micro, Lite, and Pro, there are some that are considered "optimized". You'll find those mentioned in our Nova User Guide here: https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html
The original question mentioned text-to-speech. These models do not support speech or other audio as input or output. That was announced as a future planned release during Andy Jassy's re:Invent keynote, but isn't available currently.