Hibiki is an advanced model focusing on streaming voice translation. It generates accurate translations in real time by accumulating sufficient contextual information, supporting both voice and text translation, and facilitating voice conversion. The model is based on a multi-stream architecture, capable of simultaneously processing source and target speech, producing continuous audio streams and timestamped text translations. Its main advantages include high-fidelity voice conversion, low-latency real-time translation, and compatibility with complex reasoning strategies. Hibiki currently supports translation from French to English and is suitable for efficient real-time translation scenarios, such as international conferences and multilingual live events. The model is open-source and free, making it ideal for developers and researchers.